A merge of <a target="_blank" rel="ugc" href="https://civarchive.com/models/78433?modelVersionId=83231">DonutHoleMix </a>and BE-Mix (removed from Civit, no idea why) along with <a target="_blank" rel="ugc" href="https://civarchive.com/models/33609/gothic-punk-girl">Gothic Punk Girl</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/models/6857/hitoimim">Hitoimim art style</a> (<a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/30837811">artist link</a>) loras baked inI found that using the mentioned loras with specific strength on BE-Mix resulted in an interesting look, this is that just merged into a single model.DonutHoleMix was more of an afterthought, and really only because I had to use a second checkpoint to do it in ComfyUI which I use exclusively, but I found that its CLIP model makes the results better and it allowed for a more anime-like model as wellGothic Punk Girl Lora (strength: 1) helps make more detailed clothing and makes characters cuter, no matter whether you're going for an explicitly gothic look or notHitoimim art style (v1.0, strength: 0.6) adds more detail to everything, eyes, hair, clothing, patterns, lace, frills etc. Also dramatically improves some animal body parts like tails or ears, as well as animals themselves. Can sometimes add animals unprompted.A side-effect of both loras is making the skin more pale than normal, hence the name.There is also <a target="_blank" rel="ugc" href="https://civarchive.com/models/8730">Hipoly 3d Model LoRA</a> (v2), but only at strength: 0.1, so its effect is negligibleThe Realistic model should be considered to be the main one. The Anime model doesn't carry too much weight from the loras which are essential to the effect in the realistic model. It is different enough from the realistic model or any of the component models, however.The Realistic/Anime distinction isn't very accurate, both are more on the 'realistic' side (though maybe it should be 2.5d/3d instead?), the anime one is just 'more' anime and vice versaBoth checkpoints work with booru-style prompts.Realistic Version:input: 100% DonutHoleMixmiddle: 100% BE-Mixoutput: 100% BE-MixAnime version:input: 100% DonutHoleMixmiddle: 100% DonutHoleMixoutput: 50/50% DonutHoleMix/BE-MixThe Loras are only mixed into BE-Mix before merging. DonutHole's U-Net and CLIP are unmodifiedThe CLIP model is the one from DonutHoleMix (modified with lora)The whole process is done in <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI">ComfyUI </a>using the block-merging nodeFor the exact recipes, load the checkpoint into ComfyUI via drag&amp;drop or load it as a ComfyUI workflowVAE: kl-f8-anime2 or vae-ft-mse-840000-ema-pruned for both models<h3 id="heading-871">Tips:</h3><ul><li>Since there is much focus on fine detail, the results may not look too well on lower resolutions.</li></ul>The showcased images were first generated in resolutions such as 576x832, 640x960, 640x1024, 512x1280, 896x576, 1024x640, etc., then upscaled 2 times into a second pass with 0.35-0.5 denoising (or hires-fix for AUTOMATIC1111 webui users) followed up with face restoration, then upscaled 2 times again.<ul><li>Don't go too high with denoising on hires-fix. It messes with face structure, especially at an angle, making them uglier. Even 0.3 can visibly change eye/mouth/nose shape. In my taste, always for worse.</li></ul>ps: don't mind my prompts in example images, It helps with organising them to get the framing I want, I swear

Files with SHA256: 678446496458d807cf8cb596f6cab07e70211f8952a6cf6d428f638e0b70f135