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.
V1 - Style Variant got a "soft" treatment of my hassaku pony V1.3 model .
The Style is more forced to a less basic 2d look and got enhancements in backgrounds, structure and details.
Because of that, artist tags and details on clothes of characters are less precise, especially for more complex clothing or lesser known characters. Faces of characters on the other hand should work fine, for the most part.
If you want to use artist tags or want it to look more "drawn" and less "AI generated", use the normal V1 Version.
Short: It now have a style merge, but not that much, to left freedom in the model. Also to prevent burned/artifact images, resulting in clean and smooth images.
I recommend to use clip 1 and not 2 (civit generator use clip 2), to have added extra details.
Notes:
There is sometimes some noise noticeble, because of heavy merging for better backgrounds. I fix that later (if possible, without losing to much of he backgrounds)
Eye errors/artifacts can appear, especially from far or if no eye color is prompted
Bodys can appear more detailed in compare to the faces, especially with characters. Thats a side effect of the forced less basic 2d style.
Files
hassakuXLIllustrious_v10Style.safetensors