Hassaku aims to a model with a distictive anime look, capable to do great sfw and nsfw art.
โV1 use illustrious-xl as base, versions from 0.2M up are trainined with quality prompts like masterpiece or worst quality.
โRecommended prompts in negative are "worst quality, low quality".
โ ๐๐ฏ๐ผ๐๐ ๐ง๐ต๐ถ๐ ๐ฉ๐ฒ๐ฟ๐๐ถ๐ผ๐ป โ
โถV1 - Style Variant got a "soft" treatment of my hassaku pony V1.3 model .
โฆThe Style is more forced to a less basic 2d look and got enhancements in backgrounds, structure and details.
โ 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.
โฆIf you want to use artist tags or want it to look more "drawn" and less "AI generated", use the normal V1 Version.
โฆShort: 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.
โฆI recommend to use clip 1 yand not 2 (civit generator use clip 2), to have added extra details.
โฆNotes:
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
โ
๐๐ฟ๐ฒ๐ฑ๐ถ๐: ๐๐ธ๐ฒ๐ป๐ฎ โถ https://civitai.com/user/Ikena
โ
๐๐ถ๐๐ถ๐๐ฎ๐ถ: https://civitai.com/models/140272/hassaku-xl-illustriousโ
