Please check out my <a target="_blank" rel="ugc" href="https://ko-fi.com/part_loras">Ko-Fi</a> page if you are interested in supporting me.LoRA commissions open! -&gt; <a target="_blank" rel="ugc" href="https://www.fiverr.com/partai/develop-your-custom-lora-or-loha-model-for-stable-diffusion">Fiverr</a><h3 id="heading-371">This is a LoHa LoRA! You need the <a target="_blank" rel="ugc" href="https://github.com/KohakuBlueleaf/a1111-sd-webui-locon">extension</a>! Why? They do a lot better with multi-concepts.</h3><h3 id="heading-380">SD gets her face tattoo correctly around 40-50% gens.</h3>``tattoo`` on negatives seems to help with face tattoo.<h3 id="heading-372">Trigger words for V2.20:</h3>For original clothes: &lt;lora:Viv220:0.8&gt;(vi, original-clothes, gauntlets, pink hair, goggles on head)For police uniform: &lt;lora:Viv220:0.8&gt;(vi, police uniform, policewoman, gauntlets, pink hair, hat)For arcane version: &lt;lora:Viv220:0.8&gt;(vi, arcane, bandaged arm, red hair, hood, muscular female, jacket)<h3 id="heading-373">Follow the steps in the Model Version notes to reproduce my images.</h3>Sample images generated from NothingV2.3.All negative embeds should be easy to find. and Prompts should be included in the sample images! Click the little icon in the bottom right to see it.It was trained on 100 512x512 images scraped from the internet and 20 epochs using animefull_final.Danbooru tags generated by Waifu Diffusion 1.4 Tagger and fine tuned for specific tags.

Vi - LoHa

Generate using a weight of 0.4-1 like this: &lt;lora:Viv220:0.8&gt; How I archived my generations:<ol><li>txt2img: DPM++ SDE Karras with 20 steps,512x512(can go up to 768 for wide or tall), Restore faces on (using CodeFormer weight 1.0 in Settings), Hires-fix on, to 1024x1024 (double original size) with your preferred upscaler and Denoise 0.5, CFG 7. Then send to img2img!</li><li>img2img: DPM++ SED Karras with 20 steps, Restore faces on (CodeFormer weight 1), rescale to 1536x1536, CFG 7, Denoise between 0.3-0.7 (based on how much you want to improve the image), SAME PROMPT! Send to extras when happy with img2img/inpaint results.</li><li>extras: Scale to x3 (final will be 4608x4608, I suggest going lower, I did x3 just for the samples here) Upscaler 1 - FatalAnime 4x, Upscaler 2 - SwinIR 4x with 0.10 visibility, GFPGAN 0.10 visibility, CodeFormer 0.10 visibility.</li></ol>

Files with SHA256: a2038ba4eea134494144fe6e8247c80f29ff3fa147881b3701c7709b5615bbcb