WAS

There seems to be some sort of conflict, nothing works, not even `display_image_cleaner('./') will work, same error. Something in my program (https://rebrand.ly/easy-diffusion) is conflicting with paths, but no clue what....

> @WASasquatch looks like you've resolved it? [#756 (comment)](https://github.com/huggingface/diffusers/issues/756#issuecomment-1270571541) This wasn't, unfortunately. Still getting it on every install, but only first time around. After that, it appears to be able...

It's a constant used to scale the `latents` so it can be decoded back into a image ([src](https://huggingface.co/blog/stable_diffusion)) ```python # scale and decode the image latents with vae latents =...

Thanks for the example. Is it safe to assume you can override the feature extractor and clip model of any pipe without having to reimplement your whole system for custom,...

I've been thinking for a long time that pipes [of a type] should be merged. Stable Diffusion pipeline for example should have all it's basic pipelines as one Stable Diffusion...

To add further, it's possible that the `StableDiffusionPipeline` may not even need an ID/Enum. It would be logical enough to assume it's `img2img` if a INIT is provided, and no...

> We have a long issue regarding "merging" stable diffusion pipeline into one, could you please comment there: #551 > > It would be nice if this issue could focus...

I double-checked to make sure it wasn't something I've done on the dev branch, but yes, the error is present in public branch (which hasn't received any updates to cause...

Also, is the `pip` version upgraded with negative prompts and such or will all those patches need to be re-implemented? Maybe I should just roll back to a commit?

Oh really? I was installing via **dev** (for concepts) `!pip3 install -qq diffusers["training"] transformers ftfy` (for some reason `diffusers["training"]` doesn't work with subprocess command. :( **main** (public) `subprocess.run(['pip', '-q', 'install',...