-
Notifications
You must be signed in to change notification settings - Fork 7
Description
Thank you very much for your excellent work.
When I was replicating your code, I had a problem with the model not loading in infer_style.py, so I Googled the model and converted it using convert in diffusers.
(
Run the code here https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py
with the command of python convert_original_stable_diffusion_to_diffusers.py --checkpoint_path path/to/sdxlUnstableDiffusers_v8HeavensWrathVAE.safetensors --dump_path /InstantStyle-Plus/checkpoints/sdxlUnstableDiffusers_v8HeavensWrathVAE --image_size 512 --prediction_type epsilon --from_safetensors --device cuda:0 --half
)
However, the converted folder text_encoder and other folders do not contain safetensors, and corresponding errors will be reported during runtime. How should I handle this error?

