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

[JIAOJIAYUASD]

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

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

How can I fix this promblem!

[asomoza]

I don't fully understand all that you wrote, but if you're training the LoRA with one of the diffusers scripts, you can use the --output_kohya_format arg to save it.