Skip to content

GitLab

Switch branch/tag
  1. 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
  3. 03 Jul, 2023 1 commit
    • Patrick von Platen's avatar
      Correct controlnet out of list error (#3928) · 2e8668f0
      Patrick von Platen authored 
      * Correct controlnet out of list error

* Apply suggestions from code review

* correct tests

* correct tests

* fix

* test all

* Apply suggestions from code review

* test all

* test all

* Apply suggestions from code review

* Apply suggestions from code review

* fix more tests

* Fix more

* Apply suggestions from code review

* finish

* Apply suggestions from code review

* Update src/diffusers/schedulers/scheduling_k_dpm_2_ancestral_discrete.py

* finish
      2e8668f0
  5. 28 Jun, 2023 1 commit
  7. 20 Jun, 2023 1 commit
  9. 07 Jun, 2023 1 commit
  11. 22 May, 2023 2 commits
  13. 16 May, 2023 1 commit
  15. 15 May, 2023 1 commit
  17. 12 May, 2023 1 commit
  19. 06 May, 2023 1 commit
  21. 05 May, 2023 2 commits
  23. 03 May, 2023 1 commit
  25. 27 Apr, 2023 1 commit
    • Nipun Jindal's avatar
      [2064]: Add stochastic sampler (sample_dpmpp_sde) (#3020) · fd512d74
      Nipun Jindal authored 
      

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* Review comments

* [Review comment]: Add is_torchsde_available()

* [Review comment]: Test and docs

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

---------
Co-authored-by: default avatarnjindal <njindal@adobe.com>
      fd512d74
  27. 21 Apr, 2023 1 commit
  29. 17 Apr, 2023 1 commit
  31. 14 Apr, 2023 1 commit
    • Will Berman's avatar
      ddpm custom timesteps (#3007) · b811964a
      Will Berman authored 
      add custom timesteps test

add custom timesteps descending order check

docs

timesteps -> custom_timesteps

can only pass one of num_inference_steps and timesteps
      b811964a
  33. 12 Apr, 2023 1 commit
  35. 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
  37. 10 Apr, 2023 7 commits
  39. 06 Apr, 2023 2 commits
  41. 14 Mar, 2023 1 commit
    • clarencechen's avatar
      Add support for different model prediction types in DDIMInverseScheduler (#2619) · ee71d9d0
      clarencechen authored 
      

* Add support for different model prediction types in DDIMInverseScheduler
Resolve alpha_prod_t_prev index issue for final step of inversion

* Fix old bug introduced when prediction type is "sample"

* Add support for sample clipping for numerical stability and deprecate old kwarg

* Detach sample, alphas, betas

Derive predicted noise from model output before dist. regularization

Style cleanup

* Log loss for debugging

* Revert "Log loss for debugging"

This reverts commit 76ea9c856f99f4c8eca45a0b1801593bb982584b.

* Add comments

* Add inversion equivalence test

* Add expected data for Pix2PixZero pipeline tests with SD 2

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_pix2pix_zero.py

* Remove cruft and add more explanatory comments

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      ee71d9d0
  43. 10 Mar, 2023 1 commit
  45. 09 Mar, 2023 2 commits
  47. 07 Mar, 2023 1 commit
  49. 01 Mar, 2023 1 commit
  51. 17 Feb, 2023 2 commits
  53. 16 Feb, 2023 3 commits