YiYi Xu comments

Results 502 comments of


                                            YiYi Xu

Modification on the PAG community pipeline

can we run `make quality`? will merge once the tests pass

Modification on the PAG community pipeline

cc @asomoza here

Auth token is not passable to load_textual_inversion due to named argument conflicting with accepted kwargs

Can you provide a reproducible script?

Add extra performance features for EMAModel, torch._foreach operations and better support for non-blocking CPU offloading

@sayakpaul is this good to merge?

Check for latents, before calling prepare_latents - sdxlImg2Img

should we make this consistent for all img2img pipeline then? cc @sayakpaul

Check for latents, before calling prepare_latents - sdxlImg2Img

@nileshkokane01 can you look into the test failure? seem relevant here

Check for latents, before calling prepare_latents - sdxlImg2Img

thank you:) @nileshkokane01

Stable Cascade Image to Image Pipeline

cc @kashif here does it make sense to make a img2img pipeline for Stable Cascade? from what I understand that `image` argument in Stable Cascade has a similar role as...

Use prompt tokens instead of prompt for sdxl? for the purpose of interpolation

@prismspecs does this solve your problem? https://github.com/huggingface/diffusers/discussions/7581 I'm closing this now if you still have questions, let's open a discussion https://github.com/huggingface/diffusers/discussions

single_file_utils.py#load_single_file_model_checkpoint bugs

@knoopx we just merged this PR https://github.com/huggingface/diffusers/pull/7496 can you update the diffusers and try again? if still not working, please provide a reproducible code example with inputs and checkpoints that...