Patrick von Platen

Let's leave it open until we have a colab version. We can also make use of community pipelines: https://huggingface.co/docs/diffusers/using-diffusers/custom_pipelines :-)

Yes agree! I'd be in favor of adding a function for this I think (`dis/enable_progress_bar(...)`)

@hysts would you like to try to make a PR for it? Think we could just just change: ```python for t in tqdm(self.scheduler.timesteps): ``` with: ```python for t in self.progress_bar(self.scheduler.timesteps):...

Also cc @pcuenca @ydshieh in case you would be interested in taking a look here :-)

@anton-l - what do you think here?

Agree with @osanseviero here mostly

I think we've mentioned a couple of times to remove the `init_git_repo` functionality from the unconditional training script. Also see: https://github.com/huggingface/diffusers/pull/266#discussion_r960542231 @anton-l could you please adapt the unconditional training script...

@patil-suraj @anton-l what do you think?

Let's close this for now and discuss on PR once we go multi-modality

@sam598 - is there any way you could use Linux instead? I'm not sure that we can at this stage of the library already support everything in Windows sadly :-/...