Hello everyone,

I'm finally back (though I was never really gone, just busy). Sorry for not posting anything lately. I’ve been working on my new dual-graphics-card system, and now it’s finally done. Now I can train a LoRA on one GPU while generating images with the other.

Additionally, I’ve been working on the requested LoRA, but since The Legend of Vox Machina has three seasons and many characters, it takes a while to extract all the training data. To give you a better picture: the training dataset contains roughly 4,800 images for all characters.

But enough talk — let’s start with the first character, who was also requested by another user: Allura Vysoren.

Prompt: look at "Trigger Words" on the right side 👉

Changelog: look at "About this Version" on the right side 👉

My Settings (Forge Classic)*:

*note, the example images only use high-res fix.

Checkpoint: waiNSFWIllustrious_v150

Sampler: Euler a

Scheduler: Automatic

Samplings Steps: 30

Hires.fix: R-ERSGAN 4x+Anime6B, 20 Hires steps, Denoising Strength: 0.5

Extension:

Adetailer (highly recommended)