Download
1 variant available
1,4260 1 2 3 4 5 6 7 8 9,0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
134.6K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
19.1K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
(266)
Feb 24, 2024

3.5K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
38.3K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
233.2K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
License:
CreativeML Open RAIL++-MSDXL LoRA/LoCon for Pony V6/Pony Merges, trained on Nat The Lich's style. Support the artist: Nat The Lich.
Works well at 1 weight.
Will probably do a V2 of this, trained the soft side of the style more than the painterly part.
This one has more than the previous 4 I've done because this is like my 8th attempt and I want to show it off. (old comment for v1)
What I use & settings: Base Res of 832x1216 with 2x Hires fix, 8 Hires steps & 0.25-0.3 denoise, ADetailer at 1024x1024, Vectorscope 1 Contrast, (SAG) Self Attention Guidance Default Settings, (PAG) Perturbed-Attention Guidance Default Settings, 4 CFG because of PAG.
