GitLab

* combine

* Update docs/source/en/optimization/fp16.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* reformat

* initial

* fin

* review

* inference

* feedback

* feedback

* feedback

* [docs] Replace runwayml/stable-diffusion-v1-5 with Lykon/dreamshaper-8

Updated documentation as runwayml/stable-diffusion-v1-5 has been removed from Huggingface.

* Update docs/source/en/using-diffusers/inpaint.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Replace with stable-diffusion-v1-5/stable-diffusion-v1-5

* Update inpaint.md

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* toctree

* fix

* combine

* edits

* updates

* feedback

change to 2024

* Fix typos, update, trim trailing whitespace

* Trim trailing whitespaces

* Update docs/source/en/optimization/memory.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/optimization/memory.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update _toctree.yml

* Update adapt_a_model.md

* Reverse

* Reverse

* Reverse

* Update dreambooth.md

* Update instructpix2pix.md

* Update lora.md

* Update overview.md

* Update t2i_adapters.md

* Update text2image.md

* Update text_inversion.md

* Update create_dataset.md

* Update create_dataset.md

* Update create_dataset.md

* Update create_dataset.md

* Update coreml.md

* Delete docs/source/en/training/create_dataset.md

* Original create_dataset.md

* Update create_dataset.md

* Delete docs/source/en/training/create_dataset.md

* Add original file

* Delete docs/source/en/training/create_dataset.md

* Add original one

* Delete docs/source/en/training/text2image.md

* Delete docs/source/en/training/instructpix2pix.md

* Delete docs/source/en/training/dreambooth.md

* Add original files

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* refactor

* update general optim sections

* update more sections

* few more updates

* benchmark code

* add safetensors flag

* apply review

* remove attention slicing

* apply feedback

* why mdx?

* why mdx?

* why mdx?

* no x for kandinksy either

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

* doc fixes

* fix latex

* parenthesis on inside

* Fix style rendering.

* Fix typo

* [docs] add notes for stateful model changes

* Update docs/source/en/optimization/fp16.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* link to accelerate docs for discarding hooks

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

* Change the docs to use the parent DiffusionPipeline class when loading a checkpoint using from_pretrained() instead of a child class (e.g. StableDiffusionPipeline) where possible.

* Run make style to fix style issues.

* Change more docs to use DiffusionPipeline rather than a subclass.

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

* Remove suggestion to use cuDNN benchmark in docs

* removing the wrong line

Fix typos

* Tiled VAE for high-res text2img and img2img

* vae tiling, fix formatting

* enable_vae_tiling API and tests

* tiled vae docs, disable tiling for images that would have only one tile

* tiled vae tests, use channels_last memory format

* tiled vae tests, use smaller test image

* tiled vae tests, remove tiling test from fast tests

* up

* up

* make style

* Apply suggestions from code review

* Apply suggestions from code review

* Apply suggestions from code review

* make style

* improve naming

* finish

* apply suggestions

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

* up

---------
Co-authored-by: Ilmari Heikkinen <ilmari@fhtr.org>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* enable_model_offload PoC

It's surprisingly more involved than expected, see comments in the PR.

* Rename final_offload_hook

* Invoke the vae forward hook manually.

* Completely remove decoder.

* Style

* apply_forward_hook decorator

* Rename method.

* Style

* Copy enable_model_cpu_offload

* Fix copies.

* Remove comment.

* Fix copies

* Missing import

* Fix doc-builder style.

* Merge main and fix again.

* Add docs

* Fix docs.

* Add a couple of tests.

* style

* before running make style

* remove left overs from flake8

* finish

* make fix-copies

* final fix

* more fixes

no more autocast

* [CPU offload] correct cpu offload

* [CPU offload] correct cpu offload

* finish

* finish

* Update docs/source/en/optimization/fp16.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

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

* init for korean docs

* edit build yml file for multi language docs

* edit one more build yml file for multi language docs

* add title for get_frontmatter error

* Fix links to flash attention.

* Add xformers installation instructions.

* Make link to xformers install more prominent.

* Link to xformers install from training docs.

* StableDiffusion: Decode latents separately to run larger batches

* Move VAE sliced decode under enable_vae_sliced_decode and vae.enable_sliced_decode

* Rename sliced_decode to slicing

* fix whitespace

* fix quality check and repository consistency

* VAE slicing tests and documentation

* API doc hooks for VAE slicing

* reformat vae slicing tests

* Skip VAE slicing for one-image batches

* Documentation tweaks for VAE slicing
Co-authored-by: Ilmari Heikkinen <ilmari@fhtr.org>

* 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>

* 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>

* 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>

up

* up

* uP

* uP

* make style

* Apply suggestions from code review

* up

* finish

* Fix typos

* Update examples/dreambooth/train_dreambooth.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* initial commit

* make UNet stream capturable

* try to fix noise_pred value

* remove cuda graph and keep NB

* non blocking unet with PNDMScheduler

* make timesteps np arrays for pndm scheduler
because lists don't get formatted to tensors in `self.set_format`

* make max async in pndm

* use channel last format in unet

* avoid moving timesteps device in each unet call

* avoid memcpy op in `get_timestep_embedding`

* add `channels_last` kwarg to `DiffusionPipeline.from_pretrained`

* update TODO

* replace `channels_last` kwarg with `memory_format` for more generality

* revert the channels_last changes to leave it for another PR

* remove non_blocking when moving input ids to device

* remove blocking from all .to() operations at beginning of pipeline

* fix merging

* fix merging

* model can run in other precisions without autocast

* attn refactoring

* Revert "attn refactoring"

This reverts commit 0c70c0e189cd2c4d8768274c9fcf5b940ee310fb.

* remove restriction to run conv_norm in fp32

* use `baddbmm` instead of `matmul`for better in attention for better perf

* removing all reshapes to test perf

* Revert "removing all reshapes to test perf"

This reverts commit 006ccb8a8c6bc7eb7e512392e692a29d9b1553cd.

* add shapes comments

* hardcore whats needed for jitting

* Revert "hardcore whats needed for jitting"

This reverts commit 2fa9c698eae2890ac5f8e367ca80532ecf94df9a.

* Revert "remove restriction to run conv_norm in fp32"

This reverts commit cec592890c32da3d1b78d38b49e4307aedf459b9.

* revert using baddmm in attention's forward

* cleanup comment

* remove restriction to run conv_norm in fp32. no quality loss was noticed

This reverts commit cc9bc1339c998ebe9e7d733f910c6d72d9792213.

* add more optimizations techniques to docs

* Revert "add shapes comments"

This reverts commit 31c58eadb8892f95478cdf05229adf678678c5f4.

* apply suggestions

* make quality

* apply suggestions

* styling

* `scheduler.timesteps` are now arrays so we dont need .to()

* remove useless .type()

* use mean instead of max in `test_stable_diffusion_inpaint_pipeline_k_lms`

* move scheduler timestamps to correct device if tensors

* add device to `set_timesteps` in LMSD scheduler

* `self.scheduler.set_timesteps` now uses device arg for schedulers that accept it

* quick fix

* styling

* remove kwargs from schedulers `set_timesteps`

* revert to using max in K-LMS inpaint pipeline test

* Revert "`self.scheduler.set_timesteps` now uses device arg for schedulers that accept it"

This reverts commit 00d5a51e5c20d8d445c8664407ef29608106d899.

* move timesteps to correct device before loop in SD pipeline

* apply previous fix to other SD pipelines

* UNet now accepts tensor timesteps even on wrong device, to avoid errors
- it shouldnt affect performance if timesteps are alrdy on correct device
- it does slow down performance if they're on the wrong device

* fix pipeline when timesteps are arrays with strides

* Initial version of `fp16` page.

* Fix typo in README.

* Change titles of fp16 section in toctree.

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

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

* Clarify attention slicing is useful even for batches of 1

Explained by @patrickvonplaten after a suggestion by @keturn.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Do not talk about `batches` in `enable_attention_slicing`.

* Use Tip (just for fun), add link to method.

* Comment about fp16 results looking the same as float32 in practice.

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