SDXL LoRA/LoCon for Pony V6/Pony merges, trained on Asanagi's style. Support the artist: Asanagi.
Works well at 1 weight.
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 Brightness | 1 Contrast, (SAG) Self Attention Guidance Default Settings, (PAG) Perturbed-Attention Guidance: 4 PAG Scale | 1 Rescale Pag | Partial Rescale Mode, 5 CFG because of PAG.
If you want to support me or unreleased LoRAs, guides, or settings, this is my Patreon: LUUNA
If you want to make requests or commissions for specific styles/characters you can send me a DM.
Description
FAQ
Comments (3)
just quick note if someone try use this lora in webui-forge. due to some dora/Lyco implementation issue in webui-forge it will not work(LoRA version mismatch for SDXL). try latest a1111 or comfyui.
https://github.com/lllyasviel/stable-diffusion-webui-forge/pull/608/files
Get these files (click the 3 dots > view file > download raw) and replace the ones in the indicated paths (ldm_patched/modules/lora.py & ldm_patched/modules/model_patcher.py) in the Forge folder to get DoRAs working
@LUUNA Thank u!