This repository is for testing SPO-SDXL LoRA. Simply applying it with a "weight=1.0 (default)" will help produce a high-definition image. It seems to be slightly prone to disorder in Pony-type models, but this can be mostly avoided by setting "clip skip=2" in your environment.

Downloads last month
383
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for John6666/ebara-pony-v21-sdxl-spo-lora

Adapter
(1)
this model

Spaces using John6666/ebara-pony-v21-sdxl-spo-lora 2