search

huggingface / peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
https://huggingface.co/docs/peft
Apache License 2.0
16.17k stars 1.59k forks source link

How to convert a loha safetensor trained from diffusers to webui format #1693

Closed JIAOJIAYUASD closed 4 months ago

JIAOJIAYUASD commented 5 months ago

Hello, when I finetune SDXL (actually that is InstantID) with PEFT method, I use lora、loha and lokr for PEFT in diffuser. I have a question, how to convert a loha safetensor trained from diffusers to webui format？ In the training process: the loading way: peft_config = LoHaConfig( r=args.rank, alpha=args.rank //2, target_modules=["to_k", "to_q", "to_v", "to_out.0"], ) unet = get_peft_model(unet, peft_config) when train process finished, the saving way as: unet.save_pretrained(args.output_dir)

and I get the safetensor as image

But webui can't recognize it, I can't use it in webui.

How can I fix this promblem!

BenjaminBossan commented 5 months ago

I don't have much experience with webui. Did you try running this script?

https://github.com/huggingface/peft/blob/main/examples/lora_dreambooth/convert_peft_sd_lora_to_kohya_ss.py

github-actions[bot] commented 4 months ago

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.