<h1 id="4lph4bet-next_v040-font-generation-lora-ajfovze50">4lph4bet-next_v040 Font Generation LoRA</h1><p>This LoRA was created using a custom dataset to finetune Stable Diffusion 1.5. This LoRA It will generate a grid of 88 characters in a consistent style and can be used for font generation. There is a Script for post processing and font creating using <a rel="ugc" href="https://www.calligraphr.com/">Calligraphr</a>.</p><h2 id="use-eooac8hyu">Use</h2><p>Just add the LoRA to the prompt and us the following parameters as a baseline for further iteration:</p><ul><li><p>Trigger words: 4lph4bet, typography</p></li><li><p>Sample steps: 15–35</p></li><li><p>CGF-Scale: 5–9</p></li></ul><p>The model is trained on a variety of tokes to be able to specifically generate among other characteristics:</p><ul><li><p>sans, serif</p></li><li><p>light, regular, bold</p></li><li><p>italic</p></li></ul><p>It is recommendes to use Hires fix for initial upscaling. Example parameters:</p><ul><li><p>Upscaler: R-ESRGAN 4x+ Anime6B</p></li><li><p>Hires steps: 10</p></li><li><p>Denoising strength: 0.2</p></li><li><p>Upscale by: 2</p></li></ul><h2 id="post-processing-ryniiety5">Post processing</h2><p>Use this <a rel="ugc" href="https://github.com/414design/4lph4bet_processor">Python Script</a> to create a ready-to-use template for <a rel="ugc" href="https://www.calligraphr.com/">Calligraphr</a>. Before running the script it is recommended to upscale the font grid to 4096 by 4096 pixels.</p><p>Using stable-diffusion-webui-vectorstudio for stable-diffusion-webui the grids can be vectorized directly to speed up use in traditional font creation workflows.</p><h2 id="license-19xmg3ys1">License</h2><p>This LoRA is provided under a <em>CC BY-SA 4.0</em> license.</p>

Files with SHA256: 2894e6d63133186d5da8726057f46e298ca75441a21d8dc56429073ffd01897c