MugenMaluMix SDXL

MugenMaluMixThese checkpoints are merge mixes combined with LoRA finetunes including base models:AutismMix SDXL Confetti by Austismix_anon4th tail (Hentai model) v.0.4.0 by MinthybasisOmega Pony XL anime style v1.0 by kitarzHassaku XL (Hentai model) v1.1 by IkenaFor the full merge recipes see articles:♾️ Merge Recipe for mugenMaluMix v1♾️ Merge Recipe for mugenMaluMix v2♾️ Merge Recipe for mugenMaluMix v3♾️ Merge Recipe for mugenMaluMix v4.2The intention of these Checkpoint+LoRA merges is to create a model capable of producing highly aesthetic Game Art, Anime, and Character subjects in a Fantasy style.Quality goals are to prioritise better anatomy (hands, feet particularly) and maintain the base models responsiveness to booru tags.If you have any issues running this model, its recommended to use the Forge webui: https://github.com/lllyasviel/stable-diffusion-webui-forgeAs well as this extension if you get noise outputs:https://github.com/hako-mikan/sd-webui-prevent-artifactSpecial tags:The models are receptive to triggers of LoRA included in the merge, see the full list of LoRA's in each of the merge recipe articles.Concepts:nekomata, cat girl kittunemimi, fox girl usausamimi, rabbit girl kuronagamimi, dark elf dragon girl slime girl fangs out oni

dvr-trd, ruby green emerald style, emerald iridescent opal style, opal ral-obsdn, obsidianCharacters:olohpnxl, holo, spice and wolf

nereirfpnxl, frieren nurefpnxl, fern (sousou no frieren) lebupnxl, ubel (sousou no frieren)

eihplyspnxl, sylphiette siretaryergpnxl, eris greyrat yxorpnxl, roxy migurdia enialsihgpnxl, ghislaine dedoldia rudeus greyrat elinalise dragonroad pursena adoldia rinia dedoldiaCopyrights:nier riencarnation knights of glory nier automata bravely default final fantasy tactics granblue fire emblem heroesArtists:happoubi jin lack kintadistortion gusha_s yunimaru750+ artist styles from 4th Tail checkpoint merge (with a less predictable effect)NSFW:These words help guide the results towards adult content, as pony diffusion and related checkpoints are heavily used in these checkpoints, it's best to use these if SFW is desired.Use in positive/negative prompts as needed:safe General sensitive Sensitive nsfw Questionable explicit, nsfw ExplicitQuality:Being mostly a Pony Diffusion base, the score tags still apply, though through successive merges this mix is converging on the more common masterpeice, best quality, very aesthetic, absurdres tagging standard.Recommended prompt structure:To guide the model towards generating high-aesthetic anime style images:Positive prompt:score_9, score_8_up, score_7_up, score_6_up, source anime, {{artist}} {{character}} {{copywrite}} {{tags}}, masterpeice, best quality, very aesthetic, absurdresNegative prompt:score_4, score_3, score_2, score_1, bad hands, bad feet, monochrome, greyscale, watermarkWorkflow:Adetailer extension is used in some preview images, and is highly recommended to automatically segment and upscale faces/hands/bodies as needed:--> https://github.com/Bing-su/adetailerMerge Recipe:To test out/reuse the merge recipes from v4.2 ComfyUI and several DARE extensions are required.ComfyUI JSON for the DARE base model merge and DARE LoRA finetuning have been added to the Model Training Files. ⚠️These are quite messy, and will require significant hardware to run without modification - I used a machine with 64gb of system ram.LicenseAs the license of PonyDiffusion is more strict, the model will follow the same modified version, quoting the following from the PonyDiffusion model:The following modifications have been added to Fair AI Public License:You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.). This applies to any derivative models or model merges.Explicit permission for commercial inference has been granted to CivitAi and Hugging Face