<h2 id="abigail-brand-director-of-s.w.o.r.d.-kxg565e8j">Abigail Brand, Director of S.W.O.R.D.</h2>My first attempt at creating a LoRA for a character using a small dataset (16 low-quality images) and first Illustrious Model too.Notes:<ul><li>Use with 0.8 strength (higher may cause artifacts).</li><li>Use at least the following trigger word: <code>abgelv1</code>.</li><li>For a more comic-accurate look, add: <code>green hair</code>, <code>{green eyes|sunglasses}</code>, <code>bodysuit</code>, <code>gloves</code>.</li><li>Positive prompt: <code>masterpiece, best quality, amazing quality</code></li><li>Negative prompt: <code>bad quality, worst quality, worst detail, sketch, censor</code></li></ul>Recommended settings for text-to-image:<ul><li>Sampler: Euler A (Karras)</li><li>Sampling steps: 20</li><li>CFG scale: 5–7</li></ul>Then, send your result to image-to-image with:<ul><li>Sampling steps: 30</li><li>CFG scale: 5–7</li><li>Denoising strength: up to 0.75 (lower values for a closer match to the original image)</li><li>Extras: ADetail (for face and eyes)</li></ul>Created with: <code>WAI-NSFW-illustrious-SDXL</code> But feel free to try other checkpoints as well.I hope you will enjoy using Lora. Don't forget to rate it, leave comments, and share your creations! Your feedback is always appreciated! Thanks!

Files with SHA256: 1c04b2dfbb2171b34fdb50fb6d82940a6781c37f83ad5cc0d279f48fd29e7b3a