Linoy Tsaban

some comparisons with InstantStyle:  while B-LoRA requires optimization, it can have more robust results depending on the use case+ it requires very light optimization (i.e. I used the...

@asomoza Nice! we could maybe follow up on some of the experiments/features we covered here: https://huggingface.co/blog/sdxl_lora_advanced_script I think that could be a cool avenue to explore, and targeting specific blocks...

Made a few changes to readme and inference re: making lora unet blocks generally configurable If you do mind taking a final look @apolinario @sayakpaul @asomoza , and then 🛳️

In addition to what @standardAI asked, did you try /were there other configs in which it worked ok? anything else in the logs before the error?

Ran on colab using PyTorch 2.0.1 and xformers==0.0.21 and it still failed: - `diffusers` version: 0.24.0.dev0 - Platform: Linux-5.15.120+-x86_64-with-glibc2.35 - Python version: 3.10.12 - PyTorch version (GPU?): 2.0.1+cu117 (True) -...

Hey @pedropaf! could you please specify which base model and vae you're using? (i.e. `--pretrained_model_name_or_path=$MODEL_NAME` `--pretrained_vae_model_name_or_path=$VAE_PATH`)

@NorilskMajor thanks a lot for the PR! I think it'll be great to have better support for multiple loras as you described in https://github.com/huggingface/diffusers/issues/7298

Hey @NorilskMajor! it looks like it's still failing the quality tests due to 2 lines that need to be reformatted, could you run `make fixup`?

@sayakpaul wanna take one more look?

Hi @Bhavay-2001! I'm sorry, I missed your changes after my comment. Will take a look at the notebook. Thanks!