LoRA trained on Inputwo's (@inputwo) art.
All preview images use Hires.fix
Upscale Factor: 2
Hires steps: 10
Denoising Strength: 0.2
Upscaler: 4x-AnimeSharp
Hires.fix guide and upscaler here: Fix your Blur - HiRes Models
Use with AutismMix_pony for best results.
Description
I actually took the time to learn more about training LoRAs. This version adheres to Inputwo's style far more than the previous version. This LoRA creates more visually pleasing images with AutismMix_pony while Pony Diffusion XL v6 produces images that resemble Inputwo's style more accurately
FAQ
Comments (3)
It doesn't "lowkey suck ass". Don't get down on yourself.
I'm sure you'll be making all sorts of kickass LoRas in no time!
<;)
Thanks for the support! I wrote that after I tested V1 and seeing that it was nothing like the training data. I can safely say that V2 is miles ahead of V1👍
Good!
<:)