GitLab

* Docs: refer to pre-RC version of PyTorch 1.13.0.

* Remove temporary workaround for unavailable op.

* Update comment to make it less ambiguous.

* Remove use of contiguous in mps.

It appears to not longer be necessary.

* Special case: use einsum for much better performance in mps

* Update mps docs.

* MPS: make pipeline work in half precision.

Tests: upgrade PyTorch cuda to 11.7.

Otherwise the cuda versions of torch and torchvision mismatch, and
examples tests fail. We were requesting cuda 11.6 for PyTorch, and the
default torchvision (via setup.py).

Another option would be to include torchvision in the same pip install
line as torch.

* add seed resizing to community examples

* actually add the file responsible for seed resizing

* Update training and fine-tuning docs.

* Update examples README.

* Update README.

* Add Flax fine-tuning section.

* Accept suggestion
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Accept suggestion
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* up

* up

* up

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py

* Apply suggestions from code review

* [Tests] Speed up slow tests

* Up

* up

* improve tests

* up

* finish

* upload

* add init

* up

* finish vae

* finish

* reduce loading time with device_map

* remove device_map from CPU

* uP

* fix `upsample_nearest_nhwc` for large bsz

* fix `upsample_nearest_nhwc` for large bsz

fix jnp dtype

* document cpu offloading method

* address review comments
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

tensorboard import in readme, otherwise accelerator.trackers[0] out of range
Co-authored-by: lukovnikov <lukovnikov@users.noreply.github.com>

Deprecate `init_git_repo` and `push_to_hub`, refactor `train_unconditional.py`

* [Flax] Add DreamBooth

* fix sample rng

* style

* not reuse rng

* add dtype for mixed precision training

* Add Flax example

Set train mode for text encoder

* [Flax] Add finetune Stable Diffusion

* temporary fix

* drop_last and seed

* add dtype for mixed precision training

* style

* Add Flax example

* [Accelerate model loading] Fix meta device and super low memory usage

* better naming

make input_args optional

* Add failing test for #940.

* Do not use torch.float64 in mps.

* style

* Temporarily skip add_noise for IPNDMScheduler.

Until #990 is addressed.

* Fix additional float64 error in mps.

* Improve add_noise test

* Slight edit – I think it's clearer this way.

* add textual inversion flax

* make style

* make style

* replicate vae and unet params

* make style

* minor

* save after end of training

* style

* Temporary fix
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Add Flax instruction
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Make training code usable by external scripts

Add parameter inputs to training and argument parsing function to allow this script to be used by an external call.

* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* add method to enable cuda with minimal gpu usage to stable diffusion

* add test to minimal cuda memory usage

* ensure all models but unet are onn torch.float32

* move to cpu_offload along with minor internal changes to make it work

* make it test against accelerate master branch

* coming back, its official: I don't know how to make it test againt the master branch from accelerate

* make it install accelerate from master on tests

* go back to accelerate>=0.11

* undo prettier formatting on yml files

* undo prettier formatting on yml files againn

remove tensor_format in the new version

CompVis -> diffusers script - allow converting from merged checkpoint to either EMA or non-EMA (#991)

* improve script

* up

* Add failing test for #940.

* Do not use torch.float64 in mps.

* style

* Temporarily skip add_noise for IPNDMScheduler.

Until #990 is addressed.