Skip to content

GitLab

Switch branch/tag
  1. 15 Aug, 2023 1 commit
  3. 11 Jul, 2023 1 commit
  5. 05 Jul, 2023 1 commit
    • 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
  7. 21 Jun, 2023 1 commit
  9. 05 Jun, 2023 1 commit
  11. 25 Apr, 2023 1 commit
    • Patrick von Platen's avatar
      add model (#3230) · e51f19ae
      Patrick von Platen authored 
      

* add

* clean

* up

* clean up more

* fix more tests

* Improve docs further

* improve

* more fixes docs

* Improve docs more

* Update src/diffusers/models/unet_2d_condition.py

* fix

* up

* update doc links

* make fix-copies

* add safety checker and watermarker to stage 3 doc page code snippets

* speed optimizations docs

* memory optimization docs

* make style

* add watermarking snippets to doc string examples

* make style

* use pt_to_pil helper functions in doc strings

* skip mps tests

* Improve safety

* make style

* new logic

* fix

* fix bad onnx design

* make new stable diffusion upscale pipeline model arguments optional

* define has_nsfw_concept when non-pil output type

* lowercase linked to notebook name

---------
Co-authored-by: default avatarWilliam Berman <WLBberman@gmail.com>
      e51f19ae
  13. 17 Apr, 2023 1 commit
  15. 11 Apr, 2023 1 commit
    • Patrick von Platen's avatar
      Fix config prints and save, load of pipelines (#2849) · 8b451eb6
      Patrick von Platen authored 
      * [Config] Fix config prints and save, load

* Only use potential nn.Modules for dtype and device

* Correct vae image processor

* make sure in_channels is not accessed directly

* make sure in channels is only accessed via config

* Make sure schedulers only access config attributes

* Make sure to access config in SAG

* Fix vae processor and make style

* add tests

* uP

* make style

* Fix more naming issues

* Final fix with vae config

* change more
      8b451eb6
  17. 27 Mar, 2023 1 commit
  19. 10 Mar, 2023 1 commit
  21. 01 Mar, 2023 1 commit
  23. 07 Feb, 2023 1 commit
  25. 26 Jan, 2023 1 commit
  27. 30 Nov, 2022 1 commit
  29. 25 Nov, 2022 2 commits
    • Patrick von Platen's avatar
      Allow to set config params directly in init (#1419) · 8faa822d
      Patrick von Platen authored 
      * fix

* fix deprecated kwargs logic

* add tests

* finish
      8faa822d
    • Pedro Cuenca's avatar
      Deprecate `predict_epsilon` (#1393) · d52388f4
      Pedro Cuenca authored 
      

* Adapt ddpm, ddpmsolver to prediction_type.

* Deprecate predict_epsilon in __init__.

* Bring FlaxDDIMScheduler up to date with DDIMScheduler.

* Set prediction_type as an ivar for consistency.

* Convert pipeline_ddpm

* Adapt tests.

* Adapt unconditional training script.

* Adapt BitDiffusion example.

* Add missing kwargs in dpmsolver_multistep

* Ugly workaround to accept deprecated predict_epsilon when loading
schedulers using from_pretrained.

* make style

* Remove import no longer in use.

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

* Use config.prediction_type everywhere

* Add a couple of Flax prediction type tests.

* make style

* fix register deprecated arg
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      d52388f4
  31. 24 Nov, 2022 1 commit
  33. 15 Nov, 2022 1 commit
  35. 08 Nov, 2022 2 commits
  37. 31 Oct, 2022 2 commits
  39. 24 Oct, 2022 1 commit
  41. 05 Oct, 2022 1 commit
  43. 27 Sep, 2022 1 commit
    • Pedro Cuenca's avatar
      Fix `main`: stable diffusion pipelines cannot be loaded (#655) · 235770dd
      Pedro Cuenca authored 
      * Replace deprecation warning f-string with class name.

When `__repr__` is invoked in the instance serialization of
`config_dict` fails, because it contains `kwargs` of type `<class
inspect._empty>`.

* Revert "Replace deprecation warning f-string with class name."

This reverts commit 1c4eb8cb104374bd84e43865fc3865862473799c.

* Do not attempt to register `"kwargs"` as an attribute.

Otherwise serialization could fail.
This may happen for other attributes, so we should create a better
solution.
      235770dd
  45. 22 Sep, 2022 1 commit
  47. 21 Sep, 2022 2 commits
    • Pedro Cuenca's avatar
      Return Flax scheduler state (#601) · a9fdb3de
      Pedro Cuenca authored 
      * Optionally return state in from_config.

Useful for Flax schedulers.

* has_state is now a property, make check more strict.

I don't check the class is `SchedulerMixin` to prevent circular
dependencies. It should be enough that the class name starts with "Flax"
the object declares it "has_state" and the "create_state" exists too.

* Use state in pipeline from_pretrained.

* Make style
      a9fdb3de
    • Pedro Cuenca's avatar
      Allow dtype to be specified in Flax pipeline (#600) · fb2fbab1
      Pedro Cuenca authored 
      * Fix typo in docstring.

* Allow dtype to be overridden on model load.

This may be a temporary solution until #567 is addressed.

* Create latents in float32

The denoising loop always computes the next step in float32, so this
would fail when using `bfloat16`.
      fb2fbab1
  49. 19 Sep, 2022 1 commit
  51. 17 Sep, 2022 1 commit
  53. 16 Sep, 2022 1 commit
  55. 14 Sep, 2022 1 commit
  57. 13 Sep, 2022 1 commit
  59. 08 Sep, 2022 1 commit
  61. 01 Sep, 2022 1 commit
  63. 17 Aug, 2022 1 commit
  65. 21 Jul, 2022 1 commit
  67. 20 Jul, 2022 2 commits
  69. 19 Jul, 2022 1 commit