So how to use this format with stable diffusion pipline? especial the .safetensors of lora

[sunhaha123]

No description provided.

[Narsil]

Do you mean this ?

https://huggingface.co/docs/diffusers/training/lora#inference

[Narsil]

I created a PR to enable support in diffusers. Is that what you meant ?

huggingface/diffusers#2448

[sunhaha123]

I created a PR to enable support in diffusers. Is that what you meant ?

huggingface/diffusers#2448

Absoultely not! Training lora has at least 4 methods, https://github.com/kohya-ss/sd-scripts; https://github.com/Akegarasu/lora-scripts; webui extention; https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#inference-1. Thought them are in format of safetensors, but they are not same inside!

[Narsil]

Well, LoRA are just regular weights, so there's nothing blocking from using safetensors for those.

No offense but both your links are code I have never heard about. I'm happy to help provide guidance in creating safetensors lora support in all of them, but I cannot reasonably create all the PRs in all the repos. Just understanding what's going on is going to take me too long.

But basically search of torch.load/torch.save and replace with safetensors.torch.save_file/load_file and you should be good.

[sunhaha123]

Well, LoRA are just regular weights, so there's nothing blocking from using safetensors for those.

No offense but both your links are code I have never heard about. I'm happy to help provide guidance in creating safetensors lora support in all of them, but I cannot reasonably create all the PRs in all the repos. Just understanding what's going on is going to take me too long.

But basically search of torch.load/torch.save and replace with safetensors.torch.save_file/load_file and you should be good.

I wish it was. In https://civitai.com/, most of safetensors of lora cant't be loaded in diffusers.

[Narsil]

You mean these kind of checkpoints ? https://civitai.com/models/5373/makima-chainsaw-man-lora

It seems like this is a Lora and should be already usable in SD, no ?

[khimaros]

it seems like this will soon be merged into diffusers library huggingface/diffusers#2448 and in the meantime this script may be useful: https://github.com/haofanwang/Lora-for-Diffusers/blob/main/format_convert.py

[williamberman]

@Narsil's PR adds safetensor's to our current saving and loading of lora weights. Happy to discuss adding more lora/safetensors functionality but we would need more details and would recommend a separate, more detailed issue on diffusers :)

[Narsil]

Closing the issue. Feel free to reopen