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 <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. My <a target="_blank" rel="ugc" href="https://discord.gg/zSR5FcYWWE">Discord</a> for everything related to anime models and art. If you'd like to support my work, you can do so at: <a target="_new" rel="ugc" href="https://subscribestar.adult/citrus-models">SubscribeStar</a>, every bit helps and is truly appreciated!____________________________________________________________ Supporters:Thanks to my supporters tamashiicolle, pttcot, SETI and Kodokuna_____________________________________________________Using the model:Use mostly <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/">danbooru</a> tags. No extra vae needed. For better promting on it, use this <a target="_blank" rel="ugc" href="https://aituts.com/novelai-anime-prompt-techniques/">LINK</a> or <a target="_blank" rel="ugc" href="https://lunarmimi.net/freebies/novelai-anime-girl-prompt-guide/#1basic">LINK</a>. But instead of {}, use (), <a target="_blank" rel="ugc" href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">stable-diffusion-webui</a> 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._____________________________________________________<a target="_blank" rel="ugc" href="https://rentry.org/hdgpromptassist#loras">Loras</a>:Every LoRA that is build to function on anyV3 or orangeMixes, works on hassaku too. Some can be found <a target="_blank" rel="ugc" href="https://rentry.org/hdglorarepo">here</a>, <a target="_blank" rel="ugc" href="https://gitgud.io/gayshit/makesomefuckingporn#lora-list">here</a> or on civit by <a target="_blank" rel="ugc" href="https://civarchive.com/user/lottalewds">lottalewds</a><a target="_blank" rel="ugc" href="https://civarchive.com/user/fuggy">, </a><a target="_blank" rel="ugc" href="https://civarchive.com/user/Trauter">Trauter, </a><a target="_blank" rel="ugc" href="https://civarchive.com/user/Your_computer">Your_computer</a>, <a target="_blank" rel="ugc" href="https://civarchive.com/user/ekune">ekune</a> or<a target="_blank" rel="ugc" href="https://civarchive.com/user/fuggy"> </a><a target="_blank" rel="ugc" href="https://civarchive.com/user/lykon">lykon</a><a target="_blank" rel="ugc" href="https://civarchive.com/user/fuggy">.</a>_____________________________________________________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).

Hassaku (SD1.5)

The determination of what is better/worse in compare to my other model grapefruit is more difficult, because a model can be used in varios ways and training have more impact overall, i can't test/predict everything. Some feedback would be nice.What is worse:- On some occasion, hands again- Images have sometimes a more dark and muddy look to it (see what is better)- Faces have sometimes not the details of the body and looking a bit detachedWhat is better/worse:- Less motion lines- It tents in its style on some images to be more semi-realisticWhat is better:- Better quality of images before highres (not on all, but for the majority)- Better contrasts -&gt; stronger lights and shadows (but it can create dark and muddy images).- Better skin textures- Some backgrounds like mountains looking better- On some images, backgrounds are better structuredDetails:Training with a small dataset (800 images).Vae included in the model.You can support me on my <a target="_blank" rel="ugc" href="https://patreon.com/user?u=27247323&amp;utm_medium=clipboard_copy&amp;utm_source=copyLink&amp;utm_campaign=creatorshare_creator&amp;utm_content=join_link">patreon</a>, where you can get other models of me and early access to hassaku versions.

Files with SHA256: df614cd3c2a592e5e6eb4e8dfafe83c58de750781b6390bdd6b449b73315ce4b