GitLab

* Adding support for `safetensors` and LoRa.

* Adding metadata.

* [Model offload] Add nice warning

* Treat sequential and model offload differently.

Sequential raises an error because the operation would fail with a
cryptic warning later.

* Forcibly move to cpu when offloading.

* make style

* one more fix

* make fix-copies

* up

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

* Revert "Disable ONNX tests (#2509)"

This reverts commit a0549fea.

* add external weights

* + pb

* style

* Small fixes for controlnet

* finish links

Fix convert sd 768 error (#1979)
Co-authored-by: tweeter0830 <tweeter0830@users.noreply.github.com>

* Initial commit

* removed images

* Made logging the same as save

* Removed logging function

* Quality fixes

* Quality fixes

* Tested

* Added support back for validation_epochs

* Fixing styles

* Did changes

* Change to log_validation

* Add extra space after wandb import

* Add extra space after wandb
Co-authored-by: Will Berman <wlbberman@gmail.com>

* Fixed spacing

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>

* 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>

* add scaffold
- copied convert_controlnet_to_diffusers.py from
convert_original_stable_diffusion_to_diffusers.py

* Add support to load ControlNet (WIP)
- this makes Missking Key error on ControlNetModel

* Update to convert ControlNet without error msg
- init impl for StableDiffusionControlNetPipeline
- init impl for ControlNetModel

* cleanup of commented out

* split create_controlnet_diffusers_config()
from create_unet_diffusers_config()

- add config: hint_channels

* Add input_hint_block, input_zero_conv and
middle_block_out
- this makes missing key error on loading model

* add unet_2d_blocks_controlnet.py
- copied from unet_2d_blocks.py as impl CrossAttnDownBlock2D,DownBlock2D
- this makes missing key error on loading model

* Add loading for input_hint_block, zero_convs
and middle_block_out

- this makes no error message on model loading

* Copy from UNet2DConditionalModel except __init__

* Add ultra primitive test for ControlNetModel
inference

* Support ControlNetModel inference
- without exceptions

* copy forward() from UNet2DConditionModel

* Impl ControlledUNet2DConditionModel inference
- test_controlled_unet_inference passed

* Frozen weight & biases for training

* Minimized version of ControlNet/ControlledUnet
- test_modules_controllnet.py passed

* make style

* Add support model loading for minimized ver

* Remove all previous version files

* from_pretrained and inference test passed

* copied from pipeline_stable_diffusion.py
except `__init__()`

* Impl pipeline, pixel match test (almost) passed.

* make style

* make fix-copies

* Fix to add import ControlNet blocks
for `make fix-copies`

* Remove einops dependency

* Support  np.ndarray, PIL.Image for controlnet_hint

* set default config file as lllyasviel's

* Add support grayscale (hw) numpy array

* Add and update docstrings

* add control_net.mdx

* add control_net.mdx to toctree

* Update copyright year

* Fix to add PIL.Image RGB->BGR conversion
- thanks @Mystfit

* make fix-copies

* add basic fast test for controlnet

* add slow test for controlnet/unet

* Ignore down/up_block len check on ControlNet

* add a copy from test_stable_diffusion.py

* Accept controlnet_hint is None

* merge pipeline_stable_diffusion.py diff

* Update class name to SDControlNetPipeline

* make style

* Baseline fast test almost passed (w long desc)

* still needs investigate.

Following didn't passed descriped in TODO comment:
- test_stable_diffusion_long_prompt
- test_stable_diffusion_no_safety_checker

Following didn't passed same as stable_diffusion_pipeline:
- test_attention_slicing_forward_pass
- test_inference_batch_single_identical
- test_xformers_attention_forwardGenerator_pass
these seems come from calc accuracy.

* Add note comment related vae_scale_factor

* add test_stable_diffusion_controlnet_ddim

* add assertion for vae_scale_factor != 8

* slow test of pipeline almost passed
Failed: test_stable_diffusion_pipeline_with_model_offloading
- ImportError: `enable_model_offload` requires `accelerate v0.17.0` or higher

but currently latest version == 0.16.0

* test_stable_diffusion_long_prompt passed

* test_stable_diffusion_no_safety_checker passed

- due to its model size, move to slow test

* remove PoC test files

* fix num_of_image, prompt length issue add add test

* add support List[PIL.Image] for controlnet_hint

* wip

* all slow test passed

* make style

* update for slow test

* RGB(PIL)->BGR(ctrlnet) conversion

* fixes

* remove manual num_images_per_prompt test

* add document

* add `image` argument docstring

* make style

* Add line to correct conversion

* add controlnet_conditioning_scale (aka control_scales
strength)

* rgb channel ordering by default

* image batching logic

* Add control image descriptions for each checkpoint

* Only save controlnet model in conversion script

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

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

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/en/api/pipelines/stable_diffusion/control_net.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* add gerated image example

* a depth mask -> a depth map

* rename control_net.mdx to controlnet.mdx

* fix toc title

* add ControlNet abstruct and link

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_controlnet.py
Co-authored-by: dqueue <dbyqin@gmail.com>

* remove controlnet constructor arguments re: @patrickvonplaten

* [integration tests] test canny

* test_canny fixes

* [integration tests] test_depth

* [integration tests] test_hed

* [integration tests] test_mlsd

* add channel order config to controlnet

* [integration tests] test normal

* [integration tests] test_openpose test_scribble

* change height and width to default to conditioning image

* [integration tests] test seg

* style

* test_depth fix

* [integration tests] size fixes

* [integration tests] cpu offloading

* style

* generalize controlnet embedding

* fix conversion script

* Update docs/source/en/api/pipelines/stable_diffusion/controlnet.mdx
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/pipelines/stable_diffusion/controlnet.mdx
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/pipelines/stable_diffusion/controlnet.mdx
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/api/pipelines/stable_diffusion/controlnet.mdx
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Style adapted to the documentation of pix2pix

* merge main by hand

* style

* [docs] controlling generation doc nits

* correct some things

* add: controlnetmodel to autodoc.

* finish docs

* finish

* finish 2

* correct images

* finish controlnet

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

* uP

* upload model

* up

* up

---------
Co-authored-by: William Berman <WLBberman@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: dqueue <dbyqin@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* attend and excite batch test causing timeouts

* PipelineTesterMixin argument configuration refactor

* error message text re: @yiyixuxu

* remove eta re: @patrickvonplaten

* [Tests] Fix slow tests

* [Tests] Fix slow tsets

Bring flax attention naming in sync with PyTorch.

* is_safetensors_compatible refactor

* files list comma

* Sequential cpu offload: require accelerate 0.14.0.

* Import is_accelerate_version

* Missing copy.

* Use "hub" directory for cache instead of "diffusers"

* Import cache locations from huggingface_hub

I verified that the constants are available in huggingface_hub version
0.10.0, which is the minimum we require.
Co-authored-by: Lucain Pouget <lucainp@gmail.com>

* make style

* Move cached directories to new location.

* make style

* Apply suggestions by @Wauplin
Co-authored-by: Lucain <lucainp@gmail.com>

* Fix is_file

* Ignore symlinks.

Especially important if we want to ensure that the user may want to invoke the
process again later, if they are keeping multiple envs with different
versions.

* Style

---------
Co-authored-by: Lucain Pouget <lucainp@gmail.com>

* edit controlling generation doc.

* add: demo link to pix2pix zero docs.

* refactor oanorama a bit.

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

* pix: typo.

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

* attend and excite batch test causing timeouts

* pix2pix tests, no write to fs

* [Docs] Improve safetensors

* Apply suggestions from code review

* Add 4090 benchmark (PyTorch 2.0)

* Small changes in nomenclature.

* [Safetensors] Make sure metadata is saved

* make style

* Fix tensorboard tracking with `accelerate` @ `main`

* Fix `train_unconditional.py` with accelerate from main.

* Skip variant tests (UNet1d, UNetRL) on mps.

mish op not yet supported.

* Exclude a couple of panorama tests on mps

They are too slow for fast CI.

* Exclude mps panorama from more tests.

* mps: exclude all fast panorama tests as they keep failing.

* Update train_text_to_image_lora.py

* Update train_text_to_image_lora.py

Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>

small bugfix at StableDiffusionDepth2ImgPipeline call to check_inputs and batch size calculation (#2423)

small bugfix in call to check_inputs and batch size calculation
Co-authored-by: mishka <gartsocial@gmail.com>

add: note on SDEdit

Co-authored-by: yiyixuxu <yixu310@gmail,com>

* remove author names.

* add: demo link to panorama.

Deprecation warning should only hit at version 0.15

* stable unclip integration tests turn on memory saving

* add note on turning on memory saving