{
    "activation text": "",
    "description": "Hassaku aims to be a model with a bright, clear anime style. Model focus are nsfw images, but also with a high emphasis for good looking sfw images as well. My Discord https://discord.gg/zSR5FcYWWE for everything related to anime models and art. You can support me on my patreon https://www.patreon.com/user?u=27247323 and if you are interested, we also have a collaboration of multiple AI artists named Sinful Sketch Society  https://www.patreon.com/Ikenathat you can support!My models: sudachi(flat 2d) https://civitai.com/models/85909/sudachi, koji(2d) https://civitai.com/models/41916/koji, yuzu(light semirealistic) https://civitai.com/models/67120/yuzu, grapefruit(old hentai model) https://civitai.com/models/24383Sponsors:Mage.space https://www.mage.space/ with its amazing creators program supports all kinds of creators like me! Preinstalled with 80+ high quality models, hundreds of loras and a new animation feature, join their discord community here! https://discord.gg/vazvge4vHfSupporters:Thanks to my supporters Riyu, SETI, Jelly, lawrencium_Lr103 and Kodokuna on my patreon https://patreon.com/user?u=27247323&utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=creatorshare_creator&utm_content=join_link!You can support me on my patreon https://patreon.com/user?u=27247323&utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=creatorshare_creator&utm_content=join_link, where you can get other models of me and early access to hassaku versions._____________________________________________________Using the model:Use mostly danbooru https://danbooru.donmai.us/ tags. No extra vae needed. For better promting on it, use this LINK https://aituts.com/novelai-anime-prompt-techniques/ or LINK https://lunarmimi.net/freebies/novelai-anime-girl-prompt-guide/#1basic. But instead of {}, use (), stable-diffusion-webui https://github.com/AUTOMATIC1111/stable-diffusion-webui use (). Use \"masterpiece\" and \"best quality\" in positive, \"worst quality\" and \"low quality\" in negative.My negative ones are: (low quality, worst quality:1.4) with extra monochrome, signature, text or logo when needed.Use a clip skip 1 or 2. Clip 2 is better for private parts, img2img and prompt following. Clip 1 is visually better, because i assume, the model has more time and freedom there. I use clip2.Don't use face restore and underscores _, type red eyes and not red_eyes.Don't go to really high resolutions. Every model, like hassaku, get lost in the vastness of big images and has a much higher chance to greate, as example, a second anus._____________________________________________________Loras https://rentry.org/hdgpromptassist#loras:Every LoRA that is build to function on anyV3 or orangeMixes, works on hassaku too. Some can be found here https://rentry.org/hdglorarepo, here https://gitgud.io/gayshit/makesomefuckingporn#lora-list or on civit by lottalewds https://civitai.com/user/lottalewds,  https://civitai.com/user/fuggyTrauter,  https://civitai.com/user/TrauterYour_computer https://civitai.com/user/Your_computer, ekune https://civitai.com/user/ekune or  https://civitai.com/user/fuggylykon https://civitai.com/user/lykon. https://civitai.com/user/fuggy_____________________________________________________Black result fix (vae bug in web ui): Use --no-half-vae in your command line argumentsI use a Eta noise seed delta of 31337 or 0, with a clip skip of 2 for the example images. Model quality mostly proved with sampler DDIM and DPM++ SDE Karras. I love DDIM the most (because it is the fastest).",
    "sd version": "SD1",
    "modelId": 2583,
    "sha256": "7EB674963A0D93FCEAD95905B4D658D1E94E9A36230C0C732F65C3F53D8888AA"
}