Please change base model to latest fine tuned sdxl model like juggernaut x or any other model
Opened this issue · 1 comments
putuoka commented
pipeline.py
class PuLIDPipeline:
def __init__(self, *args, **kwargs):
super().__init__()
self.device = 'cuda'
sdxl_base_repo = 'stabilityai/stable-diffusion-xl-base-1.0'
sdxl_lightning_repo = 'ByteDance/SDXL-Lightning'
self.sdxl_base_repo = sdxl_base_repo
311-code commented
Totally agree, i was able to change it in my last comment here but it was a huge pain and the IDencoder weights had mismatches, had to use diffusers version of model I trained. Used claude to work around the weights issue.
Juggnernaut x would have been me much better, lora support in gradio demo, 8 step lightning or no lightning option, and comfyui node.