
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:
unfortunately it doesn’t make that much progress overall and hands are bad. SDXL is fighting me here. Tested also some block and general merges for stabilisation. But even minimal merges results in damaging anything nsfw highly, because no other sdxl model cames close in nsfw capabilities to mine (so far i know). Without a RL sdxl model in the same lewdness liga like basilMix (chilloutMix), prevents me to correct things like degrading backgrounds (because most images in training feature only simple backgrounds). Hoped to get it more 2d like, i achieve it in some cases, but the big majority remains mostly more realistic.
训练词语:
名称: hassakuXLIllustrious_alphaV05.safetensors
大小 (KB): 6938843
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: hassakuXLSfwNsfw_alphaV05.safetensors
大小 (KB): 6938843
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success