* improve test precision
get tests passing with greater precision using lewington images
* make old numpy load function a wrapper around a more flexible numpy loading function
* adhere to black formatting
* add more black formatting
* adhere to isort
* loosen precision and replace path
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* 2x speedup using memory efficient attention
* remove einops dependency
* Swap K, M in op instantiation
* Simplify code, remove unnecessary maybe_init call and function, remove unused self.scale parameter
* make xformers a soft dependency
* remove one-liner functions
* change one letter variable to appropriate names
* Remove Env variable dependency, remove MemoryEfficientCrossAttention class and use enable_xformers_memory_efficient_attention method
* Add memory efficient attention toggle to img2img and inpaint pipelines
* Clearer management of xformers' availability
* update optimizations markdown to add info about memory efficient attention
* add benchmarks for TITAN RTX
* More detailed explanation of how the mem eff benchmark were ran
* Removing autocast from optimization markdown
* import_utils: import torch only if is available
Co-authored-by: Nouamane Tazi <nouamane98@gmail.com>
* initial commit to add imagic to stable diffusion community pipelines
* remove some testing changes
* comments from PR review for imagic stable diffusion
* remove changes from pipeline_stable_diffusion as part of imagic pipeline
* clean up example code and add line back in to pipeline_stable_diffusion for imagic pipeline
* remove unused functions
* small code quality changes for imagic pipeline
* clean up readme
* remove hardcoded logging values for imagic community example
* undo change for DDIMScheduler
Remove some unused parameter
The `downsample_padding` parameter does not seem to be used in `CrossAttnUpBlock2D` (or by any up block for that matter) so removing it.
* [Better scheduler docs] Improve usage examples of schedulers
* finish
* fix warnings and add test
* finish
* more replacements
* adapt fast tests hf token
* correct more
* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* Integrate compatibility with euler
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* 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.
* 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>
* 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>
Jonathan Rahn