<h1 id="theloraprodigy-presents">theloraprodigy presents</h1><h2 id="telepurte-lora">telepurte LoRA</h2>LoRA trained with theloraprodigy's high quality captioned dataset.Use 1:1 ratio for best results (e.g. 512x512).THIS LORA IS EXPERIMENTAL. DON'T EXPECT ANYTHING. EXPAND FOR DETAILS.The dataset is based on the "Nila", "bellamenta" and "cathrine" characters, hence you will likely not get good results for non-human prompts. You will have to adjust the prompt a lot. ❤️Like this model? <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/theloraprodigy">Support my work by buying me a coffee ☕</a> <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/theloraprodigy/commissions">Commissions also available!</a>How to use this LoRA model? (AUTOMATIC1111)<ol><li>Drop the LoRA into the "stable-diffusion-webui/models/Lora" folder and start AUTOMATIC1111.</li><li>Write your prompt as usual in e.g. text2img or img2img but also include "telepurte drawing, monochrome" in the prompt. You can use danbooru tags as well (needs a danbooru based checkpoint model). I recommend the following additional tags for best results: "simple background, white background"Example: "woman, telepurte drawing, black hair, hair over one eye, simple background, white background, monochrome".</li><li>On the right, under the "Generate" button, click on the button in the center that has an image icon and that says "Show / Hide Extra Networks" when hovering with the mouse on it.</li><li>A new section under the prompt will appear, go to the Lora tab there and select this model</li></ol>Training models requires expensive hardware and is consuming a lot of time. All of my models are free. You can support my work <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/theloraprodigy">by buying me a coffee ☕</a>

telepurte (experimental)

Experimental release

Files with SHA256: 85b9b6783c19d813a626e1e0879474981fa5482e9b1ca9c1283f450b45f6303e