GitLab

* Fix gradient checkpointing test

* more tsets

* 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>

* add sigmoid betas

* convert to torch

* add comment on source

* clean up resnet.py

* make style and quality

* minor formatting

* debug an exception

if dst_path is not a file, it will raise Exception in the function src_path.samefile:
FileNotFoundError: [Errno 2] No such file or directory: '/home/lilongwei/notebook/onnx_diffusion/vae_decoder/model.onnx'

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

* Fix tests

* remove bogus file

* 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

* handle dtype in vae and image2image pipeline

* handle dtype in add noise

* don't modify vae and pipeline

* remove the if

Otherwise, it crashes when eta > 0 with float16.

This is to ensure that the final latent slices stay somewhat consistent as more changes are introduced into the library.
Signed-off-by: James R T <jamestiotio@gmail.com>
Signed-off-by: James R T <jamestiotio@gmail.com>

The opset argument should be an `int` but was set as a `str`.

* Fix push_to_hub for dreambooth and textual_inversion

* Use repo.push_to_hub instead of push_to_hub

* Swap fp16 error to warning

Also remove the associated test

* Formatting

* warn -> warning

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

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

This reverts commit 95311501.

[Tests] Lower required memory for clip guided and fix super edge-case git pipeline module bug (#754)

* [Tests] Lower required memory

* fix

* up

* uP

This reverts commit 2e209c30.

Temporarily remove Flax modules from the public API

* [Custom Pipelines]

* uP

* make style

* finish

* finish

* remove ipdb

* upload

* fix

* finish docs

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

* finish

* final uploads

* remove unnecessary test
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: apolinario <joaopaulo.passos@gmail.com>

* use_deterministic_algorithms  for grad ckpt test

* remove eval

* Apply suggestions from code review

* Update tests/test_models_unet.py

* Better steps deprecation for LMS

* upd

* Raise an error when moving an fp16 pipeline to CPU

* Raise an error when moving an fp16 pipeline to CPU

* style

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

* Update src/diffusers/pipeline_utils.py
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Improve the message

* cuda

* Update tests/test_pipelines.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Add back-compatibility to LMS timesteps

* style

* 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 auth token from for TI test