GitLab

* add enable sequential cpu offloading to other stable diffusion pipelines

* trigger ci

* fix styling

* interpolate before converting to device to avoid breking when cpu_offload is enabled with fp16
Co-authored-by: Pedro Gengo  <pedro.gabriel.lourenco@hotmail.com>

* style again I need to stop forgething this thing

* fix inpainting bug that could cause device misalignment
Co-authored-by: Pedro Gengo  <pedro.gabriel.lourenco@hotmail.com>

* Apply suggestions from code review
Co-authored-by: Pedro Gengo  <pedro.gabriel.lourenco@hotmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* remove batch size from repeat

* repeat empty string if uncond_tokens is none

* fix inpaint pipes

* return back whitespace to pass code quality

* Apply suggestions from code review

* Fix typos.
Co-authored-by: Had <had-95@yandex.ru>

* 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>

* [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>

* k-diffusion-euler

* make style make quality

* make fix-copies

* fix tests for euler a

* Update src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* remove unused arg and method

* update doc

* quality

* make flake happy

* use logger instead of warn

* raise error instead of deprication

* don't require scipy

* pass generator in step

* fix tests

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update tests/test_scheduler.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* remove unused generator

* pass generator as extra_step_kwargs

* update tests

* pass generator as kwarg

* pass generator as kwarg

* quality

* fix test for lms

* fix tests
Co-authored-by: patil-suraj <surajp815@gmail.com>
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Allow None safety_checker when using CPU offload.

* Move safety detection to model call in Flax safety checker

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

* up

* up

* up

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

* Apply suggestions from code review

* 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>

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

* better naming

* 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

* [Onnx] support half-precision and fix bugs for onnx pipelines

* Update convert_stable_diffusion_checkpoint_to_onnx.py

* style

* fix has_nsfw_concept

* Update convert_stable_diffusion_checkpoint_to_onnx.py

* fix style

* 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.

* Minor doc update.

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

* Update README.md

Additionally add FLAX so the model card can be slimmer and point to this page

* Find and replace all

* v-1-5 -> v1-5

* revert test changes

* Update README.md
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update docs/source/quicktour.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update README.md
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/quicktour.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update README.md
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Revert certain references to v1-5

* Docs changes

* Apply suggestions from code review
Co-authored-by: apolinario <joaopaulo.passos+multimodal@gmail.com>
Co-authored-by: anton-l <anton@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* ONNX supervised inpainting

* sync with the torch pipeline

* fix concat

* update ref values

* back to 8 steps

* type fix

* make fix-copies

* begin pipe

* add new pipeline

* add tests

* correct fast test

* up

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

* Update tests/test_pipelines.py

* up

* up

* make style

* add fp16 test

* doc, comments

* up
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* finish

* up

* Apply suggestions from code review
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Update src/diffusers/pipeline_utils.py

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

* [WIP] Onnx img2img determinism

* more numpy + seed

* numpy inpainting, tolerance

* revert test workflow

* * Stabe Diffusion img2img using onnx.

* * Stabe Diffusion inpaint using onnx.

* Export vae_encoder, upgrade img2img, add test

* updated inpainting pipeline + test

* style
Co-authored-by: anton-l <anton@huggingface.co>

Rename and deprecate

* Fix Flax pipeline: width and height are ignored #838

* Fix Flax pipeline: width and height are ignored

fix nsfw bug

* up

* finish

* add more tests

* up

* up

* finish

* Remove set_format in Flax pipeline.

* Remove DummyChecker.

* Run safety_checker in pipeline.

* Don't pmap on every call.

We could have decorated `generate` with `pmap`, but I wanted to keep it
in case someone wants to invoke it in non-parallel mode.

* Remove commented line
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Replicate outside __call__, prepare for optional jitting.

* Remove unnecessary clipping.

As suggested by @kashif.

* Do not jit unless requested.

* Send all args to generate.

* make style

* Remove unused imports.

* Fix docstring.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Give more customizable options for safety checker

* Apply suggestions from code review

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

* Finish

* make style

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* up
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* update flax scheduler API

* remoev set format

* fix call to scale_model_input

* update flax pndm

* use int32

* update docstr

* [Img2Img] Fix batch size mismatch prompts vs. init images

* Remove bogus folder

* fix

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* mps: alt. implementation for repeat_interleave

* style

* Bump mps version of PyTorch in the documentation.

* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Simplify: do not check for device.

* style

* Fix repeat dimensions:

- The unconditional embeddings are always created from a single prompt.
- I was shadowing the batch_size var.

* Split long lines as suggested by Suraj.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* support bf16 for stable diffusion

* fix typo

* address review comments

* add accelerate to load models with smaller memory footprint

* remove low_cpu_mem_usage as it is reduntant

* move accelerate init weights context to modelling utils

* add test to ensure results are the same when loading with accelerate

* add tests to ensure ram usage gets lower when using accelerate

* move accelerate logic to single snippet under modelling utils and remove it from configuration utils

* format code using to pass quality check

* fix imports with isor

* add accelerate to test extra deps

* only import accelerate if device_map is set to auto

* move accelerate availability check to diffusers import utils

* format code

* add device map to pipeline abstraction

* lint it to pass PR quality check

* fix class check to use accelerate when using diffusers ModelMixin subclasses

* use low_cpu_mem_usage in transformers if device_map is not available

* NoModuleLayer

* comment out tests

* up

* uP

* finish

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

* finish

* uP

* make style
Co-authored-by: Pi Esposito <piero.skywalker@gmail.com>

* handle dtype in vae and image2image pipeline

* fix inpaint in fp16

* dtype should be handled in add_noise

* style

* address review comments

* add simple fast tests to check fp16

* fix test name

* put mask in fp16

This reverts commit 2e209c30.

Temporarily remove Flax modules from the public API

* compute text embeds per prompt

* don't repeat uncond prompts

* repeat separatly

* update image2image

* fix repeat uncond embeds

* adapt inpaint pipeline

* ifx uncond tokens in img2img

* add tests and fix ucond embeds in im2img and inpaint pipe

remove use_auth_token

* up

* uP

* uP

* make style

* Apply suggestions from code review

* up

* finish