<h1 id="aayla-secura-or-star-wars-9mivtqfj1">Aayla Secura | Star Wars</h1>This is my first LoRA. Feel free to leave some feedback and ideas for improvement.<h3 id="genereal-training-information-fco86c0we">Genereal training information</h3>Based on 30 images cropped to 768 x 768.Manually refined the captions from BLIP afterwards.Run with 100 steps per image totals in 3000 steps.Trained on SD1.5GTX1080 ~ 4hI did some basic testing, the following settings can be tried out as a baseline:<ul><li>Model: SD1.5, however, other models are working well too (Mostly tested with <a target="_blank" rel="ugc" href="https://civarchive.com/models/10752/the-allys-mix-iii-revolutions">The Ally's Mix</a>)</li><li>CFG: 6-9, mostly used 7</li><li>Steps: 22, 30, 35 worked well with 2M Karras and DDIM</li><li>768 by 768 will probably yield best results as it was trained on this dimensions</li><li>LoRA weight: 0.3 [very far away from real Aayla but works sometimes]; 0.6 [very nice middleground for getting some batches for testing]; 0.8 [also worked very nice]; 0.9 [wouldn't go higher as the results turn out weirdly]</li></ul><h3 id="styles-r9vjtgmz6">Styles</h3><ul><li>Realistic: (ultra realistic:1.1) [example image 1 and 2]</li><li>Cartoon: (cartoon:1.2) [weight 1.5 really exaggerates the cartoon look, therfore face details have to be sacrificed; example image 3, 4 with latent upscaling]</li><li>Drawing: drawing:1.1 of [pretty similar to cartoon, I personally favor cartoon]</li></ul><h3 id="promts-that-should-trigger-additional-training-data:-1kzkfjqkp">Promts that should trigger additional training data:</h3><ul><li>wearing star wars costume</li><li>wearing star wars outfit</li><li>leather headpiece</li><li>blue light saber (put this on the negative promts if you don't want blue lights everywhere)</li></ul>*most example images where upscaled with denoising around 0.55 (2 times, latent)

Aayla Secura | Star Wars

initial version, 30 images, 3000 steps, SD1.5

Files with SHA256: 5c57f7230c477a3b8dc5ac4fa402339ce6aefe9ca629e3b1da5405f9fad79142