<h1 id="yukimi-style-lora">Genzoman style LoRA</h1>Making models can be expensive. Do you like what I do? Consider supporting me on <a target="_blank" rel="ugc" href="https://www.patreon.com/Lykon275">Patreon</a> 🅿️ or feel free to <a target="_blank" rel="ugc" href="https://snipfeed.co/lykon">buy me a coffee</a> ☕ Been on my list for a long time, but I didn't want to make it since all SD1.5 models are super bad with full body images, which is what this artist likes to do the most. It would have required me to explain face inpainting etc. Luckily, now there is <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">ADetailer</a>, which made face inpaint super easy to reproduce from PNG info. I added a screen with the settings I used for the examples here, but you can also copy the generation data.Images have been generated using this LoRA at 1-1.2 weight and AnyLoRA ckpt. Trigger is <code>genzoman</code>. The lora has been used in the general prompt but also in the ADetailer prompt. Some pics were generated before I had the setting enabled to export ADetailer infos. However, I used the same settings in all of them (except I swapped 1girl with 1boy when needed).How to use LoRA's in auto1111:<ul><li>Update webui (use <code>git pull</code> <a target="_blank" rel="ugc" href="https://www.youtube.com/embed/mn8fMF10XN4?start=31&amp;end=60">like here</a> or redownload it)</li><li>Copy the file to <code>stable-diffusion-webui/models/lora</code></li><li>Select your LoRA like in <a target="_blank" rel="ugc" href="https://www.youtube.com/watch?v=-bMeyXOZwN0">this video</a></li><li>Make sure to change the weight (by default it's <code>:1</code> which is usually too high)</li></ul>

Files with SHA256: 981b088196651a39f84e54f19ae719d1ebdd4893b5b9ac8b5802272db27ccc30