<h3 id="heading-11">Version 0.3 is here!</h3>New large dataset with cherry-picked aesthetic fox- cat- wolf- girls and others cute characters, beautiful sceneries, landscapes and interiors, natural and hybrid captioning with CogVLM.Experimental fine tuning merged with some popular mixes. Focused on generating cute characters with animal ears and tails in anime style (not furry, no relations with ~fluff models).For best result write artist tag (by ..., if used) first and character tag in second. Very strong natural text capabilities, use it in combination with booru tags.V0.3 comes with general improvement of character knowledge and better anatomy. Correct tails (~90% with swimsuits/underwear/..., ~80% with general clothes, ~40% with interactions like "lifted by tail"), correct ears (right angles in side/back views, no more human ears spamming). As an added bonus - fine performance in NSFW, see examples.768 base resolution, features v-pred with all its benefits (do not forget to download YAML config and put it in the same folder with model!).Subversions:<ul><li>Main - pick this first, base version.</li><li>Juicy - produce high contrast and attractive pictures with epic sceneries, but sligtly less coherence</li><li>Alt - alternative merge, sometimes better then main in bodies, but simpler backgrounds. Best for upscale.</li><li>Soft - generates softer images</li></ul><h3 id="heading-318"></h3><h3 id="heading-319">If you are getting strange colour noise - download model config and place it in folder with safetensors file.</h3>

9th Tail

New improved version. More consistent and unusual backgrounds, more cute characters, more tails!Works with most Loras now, great performance at upscaling with multidiffusion. Features v-prediction, please download model config!Experimental fine tuning using a lot of high quality pictures mostly with (fox-, cat-, wolf-, ...) girls, merged with some popular mixes.For this version some pictures have natural-text captions made with Multimodal LLM, also the dataset was supplemented with a large number of landscapes and sceneries. This allows to improve performance, variety and control.

Files with SHA256: 0dd6181a14218d5be56df468075a26454ac31a6c667f325cfe434b0ad061eda7