Skip to content

GitLab

Switch branch/tag
  1. 06 Jul, 2023 3 commits
    • Patrick von Platen's avatar
      [SD-XL] Add new pipelines (#3859) · bc9a8cef
      Patrick von Platen authored 
      

* Add new text encoder

* add transformers depth

* More

* Correct conversion script

* Fix more

* Fix more

* Correct more

* correct text encoder

* Finish all

* proof that in works in run local xl

* clean up

* Get refiner to work

* Add red castle

* Fix batch size

* Improve pipelines more

* Finish text2image tests

* Add img2img test

* Fix more

* fix import

* Fix embeddings for classic models (#3888)

Fix embeddings for classic SD models.

* Allow multiple prompts to be passed to the refiner (#3895)

* finish more

* Apply suggestions from code review

* add watermarker

* Model offload (#3889)

* Model offload.

* Model offload for refiner / img2img

* Hardcode encoder offload on img2img vae encode

Saves some GPU RAM in img2img / refiner tasks so it remains below 8 GB.

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

* correct

* fix

* clean print

* Update install warning for `invisible-watermark`

* add: missing docstrings.

* fix and simplify the usage example in img2img.

* fix setup for watermarking.

* Revert "fix setup for watermarking."

This reverts commit 491bc9f5a640bbf46a97a8e52d6eff7e70eb8e4b.

* fix: watermarking setup.

* fix: op.

* run make fix-copies.

* make sure tests pass

* improve convert

* make tests pass

* make tests pass

* better error message

* fiinsh

* finish

* Fix final test

---------
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      bc9a8cef
    • Sayak Paul's avatar
      [Text-to-video] Add `torch.compile()` compatibility (#3949) · b62d9a1f
      Sayak Paul authored 
      * use sample directly instead of the dataclass.

* more usage of directly samples instead of dataclasses

* more usage of directly samples instead of dataclasses

* use direct sample in the pipeline.

* direct usage of sample in the img2img case.
      b62d9a1f
    • Prathik Rao's avatar
      Make `UNet2DConditionOutput` pickle-able (#3857) · de142611
      Prathik Rao authored 
      

* add default to unet output to prevent it from being a required arg

* add unit test

* make style

* adjust unit test

* mark as fast test

* adjust assert statement in test

---------

Co-authored-by: Prathik Rao <prathikrao@microsoft.com@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
Co-authored-by: default avatarroot <root@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
      de142611
  3. 05 Jul, 2023 2 commits
    • dg845's avatar
      Add Consistency Models Pipeline (#3492) · aed7499a
      dg845 authored 
      

* initial commit

* Improve consistency models sampling implementation.

* Add CMStochasticIterativeScheduler, which implements the multi-step sampler (stochastic_iterative_sampler) in the original code, and make further improvements to sampling.

* Add Unet blocks for consistency models

* Add conversion script for Unet

* Fix bug in new unet blocks

* Fix attention weight loading

* Make design improvements to ConsistencyModelPipeline and CMStochasticIterativeScheduler and add initial version of tests.

* make style

* Make small random test UNet class conditional and set resnet_time_scale_shift to 'scale_shift' to better match consistency model checkpoints.

* Add support for converting a test UNet and non-class-conditional UNets to the consistency models conversion script.

* make style

* Change num_class_embeds to 1000 to better match the original consistency models implementation.

* Add support for distillation in pipeline_consistency_models.py.

* Improve consistency model tests:
	- Get small testing checkpoints from hub
	- Modify tests to take into account "distillation" parameter of ConsistencyModelPipeline
	- Add onestep, multistep tests for distillation and distillation + class conditional
	- Add expected image slices for onestep tests

* make style

* Improve ConsistencyModelPipeline:
	- Add initial support for class-conditional generation
	- Fix initial sigma for onestep generation
	- Fix some sigma shape issues

* make style

* Improve ConsistencyModelPipeline:
	- add latents __call__ argument and prepare_latents method
	- add check_inputs method
	- add initial docstrings for ConsistencyModelPipeline.__call__

* make style

* Fix bug when randomly generating class labels for class-conditional generation.

* Switch CMStochasticIterativeScheduler to configuring a sigma schedule and make related changes to the pipeline and tests.

* Remove some unused code and make style.

* Fix small bug in CMStochasticIterativeScheduler.

* Add expected slices for multistep sampling tests and make them pass.

* Work on consistency model fast tests:
	- in pipeline, call self.scheduler.scale_model_input before denoising
	- get expected slices for Euler and Heun scheduler tests
	- make Euler test pass
	- mark Heun test as expected fail because it doesn't support prediction_type "sample" yet
	- remove DPM and Euler Ancestral tests because they don't support use_karras_sigmas

* make style

* Refactor conversion script to make it easier to add more model architectures to convert in the future.

* Work on ConsistencyModelPipeline tests:
	- Fix device bug when handling class labels in ConsistencyModelPipeline.__call__
	- Add slow tests for onestep and multistep sampling and make them pass
	- Refactor fast tests
	- Refactor ConsistencyModelPipeline.__init__

* make style

* Remove the add_noise and add_noise_to_input methods from CMStochasticIterativeScheduler for now.

* Run python utils/check_copies.py --fix_and_overwrite
python utils/check_dummies.py --fix_and_overwrite to make dummy objects for new pipeline and scheduler.

* Make fast tests from PipelineTesterMixin pass.

* make style

* Refactor consistency models pipeline and scheduler:
	- Remove support for Karras schedulers (only support CMStochasticIterativeScheduler)
	- Move sigma manipulation, input scaling, denoising from pipeline to scheduler
	- Make corresponding changes to tests and ensure they pass

* make style

* Add docstrings and further refactor pipeline and scheduler.

* make style

* Add initial version of the consistency models documentation.

* Refactor custom timesteps logic following DDPMScheduler/IFPipeline and temporarily add torch 2.0 SDPA kernel selection logic for debugging.

* make style

* Convert current slow tests to use fp16 and flash attention.

* make style

* Add slow tests for normal attention on cuda device.

* make style

* Fix attention weights loading

* Update consistency model fast tests for new test checkpoints with attention fix.

* make style

* apply suggestions

* Add add_noise method to CMStochasticIterativeScheduler (copied from EulerDiscreteScheduler).

* Conversion script now outputs pipeline instead of UNet and add support for LSUN-256 models and different schedulers.

* When both timesteps and num_inference_steps are supplied, raise warning instead of error (timesteps take precedence).

* make style

* Add remaining diffusers model checkpoints for models in the original consistency model release and update usage example.

* apply suggestions from review

* make style

* fix attention naming

* Add tests for CMStochasticIterativeScheduler.

* make style

* Make CMStochasticIterativeScheduler tests pass.

* make style

* Override test_step_shape in CMStochasticIterativeSchedulerTest instead of modifying it in SchedulerCommonTest.

* make style

* rename some models

* Improve API

* rename some models

* Remove duplicated block

* Add docstring and make torch compile work

* More fixes

* Fixes

* Apply suggestions from code review

* Apply suggestions from code review

* add more docstring

* update consistency conversion script

---------
Co-authored-by: default avatarayushmangal <ayushmangal@microsoft.com>
Co-authored-by: default avatarAyush Mangal <43698245+ayushtues@users.noreply.github.com>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      aed7499a
    • Pedro Cuenca's avatar
      Add `timestep_spacing` and `steps_offset` to schedulers (#3947) · 07c9a08e
      Pedro Cuenca authored 
      

* Add timestep_spacing to DDPM, LMSDiscrete, PNDM.

* Remove spurious line.

* More easy schedulers.

* Add `linspace` to DDIM

* Noise sigma for `trailing`.

* Add timestep_spacing to DEISMultistepScheduler.

Not sure the range is the way it was intended.

* Fix: remove line used to debug.

* Support timestep_spacing in DPMSolverMultistep, DPMSolverSDE, UniPC

* Fix: convert to numpy.

* Use sched. defaults when instantiating from_config

For params not present in the original configuration.

This makes it possible to switch pipeline schedulers even if they use
different timestep_spacing (or any other param).

* Apply suggestions from code review
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* Missing args in DPMSolverMultistep

* Test: default args not in config

* Style

* Fix scheduler name in test

* Remove duplicated entries

* Add test for solver_type

This test currently fails in main. When switching from DEIS to UniPC,
solver_type is "logrho" (the default value from DEIS), which gets
translated to "bh1" by UniPC. This is different to the default value for
UniPC: "bh2". This is where the translation happens: https://github.com/huggingface/diffusers/blob/36d22d0709dc19776e3016fb3392d0f5578b0ab2/src/diffusers/schedulers/scheduling_unipc_multistep.py#L171



* UniPC: use same default for solver_type

Fixes a bug when switching from UniPC from another scheduler (i.e.,
DEIS) that uses a different solver type. The solver is now the same as
if we had instantiated the scheduler directly.

* do not save use default values

* fix more

* fix all

* fix schedulers

* fix more

* finish for real

* finish for real

* flaky tests

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_pix2pix_zero.py

* Default steps_offset to 0.

* Add missing docstrings

* Apply suggestions from code review

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      07c9a08e
  5. 03 Jul, 2023 4 commits
  7. 02 Jul, 2023 1 commit
    • Patrick von Platen's avatar
      Add video img2img (#3900) · 62825064
      Patrick von Platen authored 
      * Add image to image video

* Improve

* better naming

* make fix copies

* add docs

* finish tests

* trigger tests

* make style

* correct

* finish

* Fix more

* make style

* finish
      62825064
  9. 30 Jun, 2023 1 commit
    • Steven Liu's avatar
      [docs] Model API (#3562) · 174dcd69
      Steven Liu authored 
      * add modelmixin and unets

* remove old model page

* minor fixes

* fix unet2dcondition

* add vqmodel and autoencoderkl

* add rest of models

* fix autoencoderkl path

* fix toctree

* fix toctree again

* apply feedback

* apply feedback

* fix copies

* fix controlnet copy

* fix copies
      174dcd69
  11. 28 Jun, 2023 4 commits
  13. 26 Jun, 2023 1 commit
  15. 22 Jun, 2023 3 commits
    • Patrick von Platen's avatar
      [Conversion] Small fixes (#3848) · 5df2acf7
      Patrick von Platen authored 
      * [Conversion] Small fixes

* Update src/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py
      5df2acf7
    • Patrick von Platen's avatar
      Correct bad attn naming (#3797) · 88d26946
      Patrick von Platen authored 
      

* relax tolerance slightly

* correct incorrect naming

* correct namingc

* correct more

* Apply suggestions from code review

* Fix more

* Correct more

* correct incorrect naming

* Update src/diffusers/models/controlnet.py

* Correct flax

* Correct renaming

* Correct blocks

* Fix more

* Correct more

* mkae style

* mkae style

* mkae style

* mkae style

* mkae style

* Fix flax

* mkae style

* rename

* rename

* rename attn head dim to attention_head_dim

* correct flax

* make style

* improve

* Correct more

* make style

* fix more

* mkae style

* Update src/diffusers/models/controlnet_flax.py

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

---------
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
      88d26946
    • Sayak Paul's avatar
      fix: random module seeding (#3846) · 13e781f9
      Sayak Paul authored
      13e781f9
  17. 21 Jun, 2023 3 commits
  19. 20 Jun, 2023 1 commit
  21. 19 Jun, 2023 1 commit
  23. 16 Jun, 2023 1 commit
  25. 15 Jun, 2023 5 commits
  27. 13 Jun, 2023 1 commit
  29. 12 Jun, 2023 3 commits
  31. 08 Jun, 2023 2 commits
  33. 07 Jun, 2023 2 commits
  35. 06 Jun, 2023 2 commits