<h2>My First Lora: Tiana Upcheva</h2>TL;DR:<ol><li>This is my first attempt at training a LoRA - Would love CONSTRUCTIVE feedback</li><li>Trained using rMadArt (SD1.5) (v4.0 | <a target="_blank" rel="ugc" href="https://civarchive.com/models/18208?modelVersionId=22662">2BD42F315F</a> specifically)</li><li>34 High Res images used, hand captioned</li><li>3,400 total Steps</li><li>Should I make more LoRAs?</li></ol>Settings:<ul><li>CFG: Seems pretty flexible, but thoroughly tested on 5 - 9 CFG</li><li>Weight: LoRA weight works fine at 1.0, but as per most LoRA, 0.7 gives you the best results</li><li>Model Checkpoints: Although trained on rMadArt, I've tested with a number of other models and it seems to play very nicely</li><li>Trigger Word: No trigger word needed, but if you have issues, use 'Tiana Upcheva', especially at the front.</li></ul>Usage:<ul><li>Non-commercial</li><li>Don't be a dick with your renders</li><li>The intention of this LoRA if for creating tasteful art and fan art</li><li>Any request by Tiana Upcheva to remove this will be honoured immediately</li></ul>Contact/Questions:Send through to contact&lt;dot&gt;hotdog800&lt;at&gt;gmail&lt;dot&gt;com

Tiana Upcheva | Tijana Upčeva (The Ark | The Outpost)

First and likely only versions. Full details in Description

Files with SHA256: e0ede3c78238f6fa79c68d9b6caf79174ed16193f5b815df669cdb3b2385d1f0