<h2 id="the-first-thing-you-should-do-after-you-start-using-the-lora-is-to-go-to-one-of-the-artist's-pages-and-leave-a-few-nice-words-under-one-of-their-artworks.-that's-a-rule-now-support-the-artist!-0yeunb2to">The first thing you should do after you start using the LoRA is to go to one of the artist's pages and leave a few nice words under one of their artworks. That's a rule now - support the artist!</h2><h3 id="artist's-resources:-aft3mi3k8">Artist's resources:</h3><a target="_blank" rel="ugc" href="https://www.pixiv.net/en/users/643024">https://www.pixiv.net/en/users/643024</a><a target="_blank" rel="ugc" href="https://x.com/nagumoya_web">https://x.com/nagumoya_web</a><hr />WotBActually one of my favorite hentai artists. Really glad that I finally updated the style for v-pred. :3 Recommended samplers:<ul><li>DPM++ 2S a ★</li><li>DPM++ 2S Ancestral CFG++</li><li>Euler Ancestral CFG++</li><li>DPM++ SDE CFG++</li><li>Res Solver</li><li>DEIS</li><li>DPM++ 2M SDE Turbo</li><li>DPM++ 2S Ancestral Comfy</li></ul>Recommended checkpoint:<a target="_blank" rel="ugc" href="https://civarchive.com/models/1201815/nai-xl-vpred10-2d-accelerated?modelVersionId=1412644">NAI-XL vpred1.0 2d accelerated "Final" version</a>Base <a target="_blank" rel="ugc" href="https://civarchive.com/models/833294/noobai-xl-nai-xl">V-pred noob</a> is kinda fine too but not really recommended.Recommended upscale options:Upscaler: <a target="_blank" rel="ugc" href="https://huggingface.co/FacehugmanIII/4x_foolhardy_Remacri">foolhardy Remacri</a> or <a target="_blank" rel="ugc" href="https://huggingface.co/uwg/upscaler/blob/main/ESRGAN/lollypop.pth">Lollypop </a>or <a target="_blank" rel="ugc" href="https://huggingface.co/Akumetsu971/SD_Anime_Futuristic_Armor/blob/main/4x_fatal_Anime_500000_G.pth">Fatal Anime</a>Upscale by: from 1.25 to 2.Hires steps - half of your Sampling steps.Denoising strength - I usually set the value to 0.33, but it depends on what Hires sampling method you use.Hires sampling method: DPM++ SDE CFG++ for highlighting details or DDPM for a nice smoothing.<hr />If you found the LoRA interesting or somehow useful, consider supporting me by joining my <a target="_blank" rel="ugc" href="https://t.me/NortromDTS">Telegram channel</a>. I post thoughts there and do streams of LoRA making.

Tsumagomi Izumo / Nagumoya Style Mimic | V-Pred B-LoRA

Requires upscaling since dataset had low quality images.

MCNSTsumagomB.safetensors

Wormy Members

The following is an unedited description exported from civitAI.=============================================================The first thing you should do after you start using the LoRA is to go to one of the artist's pages and leave a few nice words under one of their artworks. That's a rule now - support the artist!Artist's resources:<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://www.pixiv.net/en/users/643024">https://www.pixiv.net/en/users/643024</a><a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://x.com/nagumoya_web">https://x.com/nagumoya_web</a>WotBActually one of my favorite hentai artists. Really glad that I finally updated the style for v-pred. :3Recommended samplers:<ul><li>DPM++ 2S a ★</li><li>DPM++ 2S Ancestral CFG++</li><li>Euler Ancestral CFG++</li><li>DPM++ SDE CFG++</li><li>Res Solver</li><li>DEIS</li><li>DPM++ 2M SDE Turbo</li><li>DPM++ 2S Ancestral Comfy</li></ul>Recommended checkpoint:<a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/1201815/nai-xl-vpred10-2d-accelerated?modelVersionId=1412644">NAI-XL vpred1.0 2d accelerated "Final" version</a>Base <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://civitai.com/models/833294/noobai-xl-nai-xl">V-pred noob</a> is kinda fine too but not really recommended.Recommended upscale options:Upscaler: <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://huggingface.co/FacehugmanIII/4x_foolhardy_Remacri">foolhardy Remacri</a> or <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://huggingface.co/uwg/upscaler/blob/main/ESRGAN/lollypop.pth">Lollypop </a>or <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://huggingface.co/Akumetsu971/SD_Anime_Futuristic_Armor/blob/main/4x_fatal_Anime_500000_G.pth">Fatal Anime</a>Upscale by: from 1.25 to 2.Hires steps - half of your Sampling steps.Denoising strength - I usually set the value to 0.33, but it depends on what Hires sampling method you use.Hires sampling method: DPM++ SDE CFG++ for highlighting details or DDPM for a nice smoothing.If you found the LoRA interesting or somehow useful, consider supporting me by joining my <a target="_blank" rel="ugc noopener noreferrer nofollow" href="https://t.me/NortromDTS">Telegram channel</a>. I post thoughts there and do streams of LoRA making.

Requires upscaling since dataset had low quality images. 

Files with SHA256: cad8a33c3a6214142fbd48c88eb4803dffeb4e00d67401e4b976c9e875c5142e