GitLab

Add extra performance features for EMAModel, torch._foreach operations and better support for non-blocking CPU offloading (#7685)

* Add support for _foreach operations and non-blocking to EMAModel

* default foreach to false

* add non-blocking EMA offloading to SD1.5 T2I example script

* fix whitespace

* move foreach to cli argument

* linting

* Update README.md re: EMA weight training

* correct args.foreach_ema

* add tests for foreach ema

* code quality

* add foreach to from_pretrained

* default foreach false

* fix linting

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

post release

* post release v0.28.0

* style

* 7879 - adjust documentation to use naruto dataset, since pokemon is now gated

* replace references to pokemon in docs

* more references to pokemon replaced

* Japanese translation update

---------
Co-authored-by: bghira <bghira@users.github.com>

A new function compute_dream_and_update_latents has been added to the
training utilities that allows you to do DREAM rectified training in line
with the paper https://arxiv.org/abs/2312.00210. The method can be used
with an extra argument in the train_text_to_image.py script.

Co-authored-by: Jimmy <39@🇺🇸.com>

* 7529 do not disable autocast for cuda devices

* Remove typecasting error check for non-mps platforms, as a correct autocast implementation makes it a non-issue

* add autocast fix to other training examples

* disable native_amp for dreambooth (sdxl)

* disable native_amp for pix2pix (sdxl)

* remove tests from remaining files

* disable native_amp on huggingface accelerator for every training example that uses it

* convert more usages of autocast to nullcontext, make style fixes

* make style fixes

* style.

* Empty-Commit

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

* post-release

* quality

switch to logger.warning

* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add tags for diffusers training

* add dora tags for drambooth lora scripts

* style

Update copyright information and fix typos in text_to_image examples

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

* standardize model card

* fix base_model

* post release

* style

* Empty-Commit

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

change to 2024

* fix minsnr implementation for v-prediction case

* format code

* always compute snr when snr_gamma is specified

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

* added unwrapper

* fiz typo

* post release

* style

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

* Post Release: v0.24.0

* post pone deprecation

* post pone deprecation

* Add model_index.json

* add variant

* add variant

* Apply suggestions from code review

* reformat

* fix: textual_inversion.py

* fix: variant in model_info

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

* post release

* fix: variant test

* up

* fix: test

post release

Min-SNR Gamma: correct the fix for SNR weighted loss in v-prediction by adding 1 to SNR rather than the resulting loss weights
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* fix: how print training resume logs.

* propagate changes to text-to-image scripts.

* propagate changes to instructpix2pix.

* propagate changes to dreambooth

* propagate changes to custom diffusion and instructpix2pix

* propagate changes to kandinsky

* propagate changes to textual inv.

* debug

* fix: checkpointing.

* debug

* debug

* debug

* back to the square

* debug

* debug

* change condition order.

* debug

* debug

* debug

* debug

* revert to original

* clean

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

add compute_snr() to training utils.

* merge with main

* fix flax example

* fix onnx example

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

Co-authored-by: bghira <bghira@users.github.com>

* [Release 0.21] Bump version

* fix & remove

* fix more

* fix all, upload

* add: utility for image grid.

* add: return type.

* change necessary places.

* add to utility page.

Co-authored-by: AisingioroHao0 <1286098622@qq.com>

* 0.20.0dev0

* make style

* Multiply lr scheduler steps by `num_processes`.

* Stop multiplying steps by gradient accumulation.

* refactor: readme serialized from the example when push_to_hub is True.

* fix: batch size arg.

* a bit better formatting

* minor fixes.

* add note on env.

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

* condition wandb info better

* make mixed_precision assignment in cli args explicit.

* separate inference block for sample images.

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

* address more comments.

* autocast mode.

* correct none image type problem.

* ifx: list assignment.

* minor fix.

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

* manual check for checkpoints_total_limit instead of using accelerate

* remove controlnet_conditioning_embedding_out_channels

* relax tolerance slightly

* correct incorrect naming

* Post release

* Post release