日本語解説は下方にありますNonet is a miscellaneous Noob-based Eps merge model that can be found anywhere.Basically, if you follow the usage of Illustrious eps, you can use it without any problem.Although not limited to this model, I feel that it is necessary to adjust the quality prompts in a timely manner while watching the output, as too much quality prompting can stiffen the atmosphere.・v010 : Just merged existing models.・v020 : Based on v010 and trained by lametta・v034 : Reviewed v020 material.・v036 : Re-merged v034 and added more ”featureless25DMix_v10”・v050 : This is based on Panettone_v021, which was merged as a joke, with a few tweaks. (Panettone is uploaded to huggingface)When using Latent in v050, you may need to set the Denoising strength a little higher or the output may be blurry. ( &gt;0.7 )<h2 id="merged-recipe-xja9r8hub">merged recipe</h2><h3 id="v010-nbz5su5nf">・v010</h3>lilybreed_v10 + (kiwimixXL_v3 - daisybreed_v10) = AA + catCarrier_v20 = BcatTowerNoobaiXL_v10 + whynotIlluWainoob_v30 = CillustriousXLPersonalMerge_v30Noob10based + sakuraplatinum_v20241117 = DobsessionIllustrious_v30 + holyMixIllustriousxl_v1 = Edaisybreed_v10 + dreammix_v10 = FC + D + E + F = GB + G = Nonnette_v010VAE: liquid111vae_sdxl9745<h3 id="v020-8njoot2ym">・v020</h3>Fine tuning nonnette_v010 with 520 lametta output images = AntrMIXIllustriousXL_xii + rillusmRealistic_v11 = BMerging B with Lora created from 60 lametta output images = Csakuraplatinum_v20241117 + waiNSFWIllustrious_v70 = DMerge Lora created from 60 lametta output images into D = EA + C = FA + E = GF + G = nonette_v020VAE: liquid111vae_sdxl9745<h3 id="v034-z4fmqhf4r">・v034</h3>Fine tuning Rillusm Realistic Illustrious v1.1 with 600 lametta output images = AFine tuning exploits_v1 with 600 lametta output images = BFine tuning catTowerMIX with 600 lametta output images = CA + B + C ＝ DD + mergeijPONYIL_ilV10VAE = EE + B = Nonnette_v034VAE: xlVAEC_f2<h3 id="v036-a5081s8fx">・v036</h3>Fine tuning catTowerMIX with 600 lametta output images = A (Same as C in v034)nonnette_v034 + A = BB + featureless25DMix_v10 = nonnette_v036VAE: xlVAEC_f2<h3 id="v050-cqtqnvg21">・v050</h3>NTR MIX v4.0 + Obsession v3.1 = AA + noolpoAI_vpred_test0.4test3 = BB + Panettone_v021 = CFine tuning exploits_v1 with 600 lametta output images = DFine tuning catTowerMIX with 600 lametta output images = ED + E = FC + F = Nonnette_v050VAE: xlVAEC_f2Thanks to the authors of each of these wonderful models !!Thanks to those who generate and post to the gallery. It gives us a sense of possibilities that even the person who merged them was unaware of.<hr />ノネットはどこにでもあるような雑多なNoob系Epsマージモデルです。基本的にはIllustrious eps の使い方に従ってもらえれば問題なく使用できると思います。このモデル標準の絵柄にIllustrious（Noob）が内包しているデータをうまく組み合わせて使用することを前提としてマージしてあります。特定のキャラクターなどを呼び出してといった使い方は他のモデルに及びません。このモデルに限ったことではないですが、クオリティプロンプト類をガチガチに詰め込むと出力が固くなるように感じるので様子を見ながら盛り込むと良いかもしれません。（サンプルは割とガチガチに盛ってありますが）・v010：既存モデルをマージしただけ・v020：v010をlamettaの出力画像で学習させたもの・v034：v020の学習素材を見直ししてリニューアル・v036：v034を再マージして「featureless25DMix_v10」をちょい足ししたもの・v050：悪ふざけでマージしたPanettone_v021をベースに調整を施したもの(Panettoneはhuggingfaceにアップされています)v050ではLatentでHires. fixした際にややぼやけた出力になることがあります。その時はDenoising strengthを高めの値に設定してください（0.7以上とか）<h2 id="-cinllfd1l">マージレシピ</h2><h3 id="v010-cd7gfrd7b">・v010</h3>lilybreed_v10 + (kiwimixXL_v3 - daisybreed_v10) = AA + catCarrier_v20 = BcatTowerNoobaiXL_v10 + whynotIlluWainoob_v30 = CillustriousXLPersonalMerge_v30Noob10based + sakuraplatinum_v20241117 = DobsessionIllustrious_v30 + holyMixIllustriousxl_v1 = Edaisybreed_v10 + dreammix_v10 = FC + D + E + F = GB + G = nonnette_v010VAE: liquid111vae_sdxl9745<h3 id="v020-6k4h6apu0">・v020</h3>nonnette_v010をlamettaの出力画像520枚でFine tuning = AntrMIXIllustriousXL_xii + rillusmRealistic_v11 = BBにlamettaの出力画像60枚から作成したLoraをマージ = Csakuraplatinum_v20241117 + waiNSFWIllustrious_v70 = DDにlamettaの出力画像60枚から作成したLoraをマージ = EA + C = FA + E = GF + G = nonette_v020VAE: liquid111vae_sdxl9745<h3 id="v034-wfapzwe95">・v034</h3>Rillusm Realistic Illustrious v1.1をlamettaの出力画像600枚でFine tuning = Aexploits_v1をlamettaの出力画像600枚でFine tuning = BcatTowerMIXをlamettaの出力画像600枚でFine tuning = CA + B + C ＝ DD + mergeijPONYIL_ilV10VAE = EE + B = Nonnette_v034VAE: xlVAEC_f2<h3 id="v036-5qgmd79e1">・v036</h3>catTowerMIX を600枚のlamettaに出力によりFine tuning = A (v034のCと同じもの）nonnette_v034 + A = BB + featureless25DMix_v10 = nonnette_v036VAE: xlVAEC_f2<h3 id="v050-qhyqbr9o2">・v050</h3>NTR MIX v4.0 + Obsession v3.1 = AA + noolpoAI_vpred_test0.4test3 = BB + Panettone_v021 = Cexploits_v1をlamettaの出力画像600枚でFine tuning = D（v034のそれと同じ）catTowerMIXをlamettaの出力画像600枚でFine tuning = E（v034のそれと同じ）D + E = FC + F = Nonnette_v050VAE: xlVAEC_f2上記の素晴らしいモデルを作成してくださった方々に感謝いたします。どうもありがとう！生成画像をギャラリーに投稿してくださる方にも感謝。マージした本人もこんな画像生成できるんだ！？って新たなインスピレーションを得ることが出来ます。

Nonnette

The number 4 was omitted because it is not auspicious in Japan... This is a joke: the 040 lineage used up all the numbering in the experiment.

Files with SHA256: 0c265fef56044cd465372ce021839c3533ed3426a57d544d59bad16117374ff8