Hassaku aims to be a anime model with a bright and distinct anime style.
You can run Hassaku XL and use its API on SinkIn: https://sinkin.ai/m/JWknjgr
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 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
_____________________________________________________
Supporters:
Thanks to my supporters Riyu, SETI and Kodokuna on my patreon!
_____________________________________________________
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 below version V1 and Illustrious-XL & WAI-NSFW-illustrious-SDXL beginning from V1:
Fair AI Public License 1.0-SD
V2 is trained on its own and don't include any merge, just Illustrious-XL 0.1, but trained to include newer or missing characters, which also use the Fair AI Public License 1.0-SD license.
Because my 2.2 Version needs a bit more time then expected. I made this fixed version of 2.1. Issues of this version was a to high style merge overall, resulting in unexpected issues with samplers and unwanted side effects.
I reduced the style merge significatly and merged style A in, because style A is overall more liked. Not only because its more stable, but also for its simpler but still detailed style.
2.1fix should have a lot less issues sampler side and resembles style A more or less in some aspects. Drawback of mergin A back is, that newer characters are getting erased in this fixed version. But that seems for most not that big of a problem, especially with the use of loras.
Note: Fixed Style is weaker on the fix version, the variety of different styles that can appear is much higher. If you don't like that faces can appear more realistic, put nose into the negatives.
Files
hassakuXLIllustrious_v21fix.safetensors