Hassaku XL (Illustrious)版本beta V0.4 (ID: 325904)

Hassaku aims to a model with a distictive anime look, capable to do great sfw and nsfw art.

V1 use illustrious-xl as base, versions from 0.2M up are trainined with quality prompts like masterpiece or worst quality. Recommended prompts in negative are "worst quality, bad quality" and masterpiece in positiv. There is also my pony xl hentai variant.

My Discord for everything related to anime models and art. You can support me on my patreon.

My models: hassaku, sudachi(flat 2d), koji(2d), yuzu(light semirealistic), grapefruit(old hentai model)

_____________________________________________________

Supporters:

Thanks to my supporters Riyu, SETI and Kodokuna on my patreon!

You can support me on my patreon, where you can get other models of me and early access to hassaku versions.

_____________________________________________________

Using the model:

• Model is trained with images with minimal disruptive features like floating texts, logos, speak bubbles and signatures as possible. If such features appearing in a image, please use prompt "signature" as negative.

• Excluded metadata and franchise tags, don't use them. meta data -> something like "highres", franchise tags like "re:zero kara hajimeru isekai seikatsu" are pruned on characters like "rem_(re:zero)".

• Here are some good resolution options for SDXL:

  • 1024 x 1024

  • 1152 x 896

  • 896 x 1152

  • 1216 x 832

  • 832 x 1216 (most recommended)

  • 1344 x 768

  • 768 x 1344

  • 1536 x 640

  • 640 x 1536

License info:

Because it merges ANIMAGINE XL 3.0 with 0.2M and Illustrious-XL & WAI-NSFW-illustrious-SDXL on V1:
Fair AI Public License 1.0-SD

描述:

Version v0.4 is right, decided to upload my current training state up, instead to put it up on my patreon, skipping my 0.3 model. Trained on 650k questionable and explizit images, as result, it is much more lewd then before and shows breast much more willingly (sometimes a bit to much). Adding now much much more sfw images into my dataset.

Goal was to make nsfw more stable with better formed out details. Image composition doesn't changed much, but the model is overall much more responsive to artist tags and better at some character likeness.

Animagine (my compare model for now), is in my oppinion better at sfw works and does make more details at some prompts. Want to make it even in capabilities.

训练词语: