[SD 2.1 768][Checkpoint]coloring-book coloring-book
<p><strong>About model</strong><br />A simple model trained on a custom dataset containing over 100 coloring book type images.</p><p>If you enjoy this model and would like me to improve on it, <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/mrhup">buy me a coffe </a>☕</p><p><br /><strong>Installation:</strong></p><p>Download both the ckpt and yaml files. Ensure that the same naming pattern is used and copy them under models/Stable-Diffusion path in your local/cloud SD installation. Stable Diffusion 2.1 is required for the model to work correctly.<br /></p><p><strong>Black images issue:</strong></p><p>2.1 models need to have a web-ui config modified - if you are getting <strong>black images </strong>- go to your config file and add to COMMANDLINE_ARGS= <code>--no-half</code> - potentially it could work with <code>--xformers</code> instead (if supported). This line might slow your generations a bit but will not affect negatively your output.</p><p></p><p><strong>Prompt suggestion:</strong></p><p><code>bichon havanese wearing sunglasses COLR_001, (((white background))), coloring book, line art, high resolution, black and white, colorless</code></p><p>Negative: <code>((watermark)), (text), color, shading, gradient, shadows, transparency, noisy, blurred</code></p>
页:
[1]