WAS

Try using `joblib` and cache each pipe to disk. It will cache the pipe, model, and plotted memory to disk, and they load in ~2 seconds (1second on my system,...

> This should cut loading time by 80-90% . Soon we'll have this enabled by default (cc @patil-suraj ) Wouldn't that be a bad idea since it's not compatible with...

Well, I have, hence the error-ing method I cited which gets triggered, which cannot be a half-float on CPU. There are lot of quirks with using CPU with diffusers right...

> > Try using `joblib` and cache each pipe to disk. It will cache the pipe, model, and plotted memory to disk, and they load in ~2 seconds (1second on...

The issue with pickle is it doesn't have memory mapping, for the objects in RAM/VRAM. Joblib takes the entire state of an object and caches it. Good for production dev,...

This is a really cool feature, and would be awesome in diffusers.

> ```python > from diffusers import logging > > logging.set_verbosity_error() > ``` This only seems to stop **one** of the safety checker warnings, others and futurewarning are still coming through...

I have been trying to get clip guidance into img2img and inpaint for weeks now, to no avail, and it's getting super frustrating. I personally find text2img as a novelty...

And don't you think that may have been a short sight in "community" development and usage through the API? It seems more intuitive for custom pipelines to be modules to...

This is pretty cool, but I would think the CLIP Interrogator isn't powerful enough, or optimized enough. It often trips out, and provides rubbish prompts for real images, let alone...