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 2 commits
  5. 20 Jun, 2023 1 commit
  7. 15 Jun, 2023 1 commit
  9. 06 Jun, 2023 1 commit
    • Isotr0py's avatar
      Support views batch for panorama (#3632) · 11b3002b
      Isotr0py authored 
      

* support views batch for panorama

* add entry for the new argument

* format entry for the new argument

* add view_batch_size test

* fix batch test and a boundary condition

* add more docstrings

* fix a typos

* fix typos

* add: entry to the doc about view_batch_size.

* Revert "add: entry to the doc about view_batch_size."

This reverts commit a36aeaa9edf9b662d09bbfd6e18cbc556ed38187.

* add a tip on .

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      11b3002b
  11. 05 Jun, 2023 1 commit
  13. 30 May, 2023 3 commits
  15. 26 May, 2023 1 commit
    • Patrick von Platen's avatar
      [Stable Diffusion Inpainting] Allow standard text-to-img checkpoints to be... · d114d80f
      Patrick von Platen authored 
      [Stable Diffusion Inpainting] Allow standard text-to-img checkpoints to be useable for SD inpainting (#3533)

* Add default to inpaint

* Make sure controlnet also works with normal sd for inpaint

* Add tests

* improve

* Correct encode images function

* Correct inpaint controlnet

* Improve text2img inpanit

* make style

* up

* up

* up

* up

* fix more
      d114d80f
  17. 24 May, 2023 1 commit
    • Isotr0py's avatar
      Fix panorama to support all schedulers (#3546) · a94977b8
      Isotr0py authored 
      * refactor blocks init

* refactor blocks loop

* remove unused function and warnings

* fix scheduler update location

* reformat code

* reformat code again

* fix PNDM test case

* reformat pndm test case
      a94977b8
  19. 23 May, 2023 1 commit
    • Pedro Cuenca's avatar
      Run `torch.compile` tests in separate subprocesses (#3503) · bde2cb5d
      Pedro Cuenca authored 
      * Run ControlNet compile test in a separate subprocess

`torch.compile()` spawns several subprocesses and the GPU memory used
was not reclaimed after the test ran. This approach was taken from
`transformers`.

* Style

* Prepare a couple more compile tests to run in subprocess.

* Use require_torch_2 decorator.

* Test inpaint_compile in subprocess.

* Run img2img compile test in subprocess.

* Run stable diffusion compile test in subprocess.

* style

* Temporarily trigger on pr to test.

* Revert "Temporarily trigger on pr to test."

This reverts commit 82d76868ddf9cc634a9f14b2b0aef1d5433cd750.
      bde2cb5d
  21. 22 May, 2023 1 commit
    • Patrick von Platen's avatar
      Refactor full determinism (#3485) · 51843fd7
      Patrick von Platen authored 
      * up

* fix more

* Apply suggestions from code review

* fix more

* fix more

* Check it

* Remove 16:8

* fix more

* fix more

* fix more

* up

* up

* Test only stable diffusion

* Test only two files

* up

* Try out spinning up processes that can be killed

* up

* Apply suggestions from code review

* up

* up
      51843fd7
  23. 17 May, 2023 2 commits
    • Glaceon-Hyy's avatar
      Add inpaint lora scale support (#3460) · 88295f92
      Glaceon-Hyy authored 
      

* add inpaint lora scale support

* add inpaint lora scale test

---------
Co-authored-by: default avataryueyang.hyy <yueyang.hyy@alibaba-inc.com>
      88295f92
    • Rupert Menneer's avatar
      Adding 'strength' parameter to StableDiffusionInpaintingPipeline (#3424) · c09c4f3a
      Rupert Menneer authored 
      

* Added explanation of 'strength' parameter

* Added get_timesteps function which relies on new strength parameter

* Added `strength` parameter which defaults to 1.

* Swapped ordering so `noise_timestep` can be calculated before masking the image

this is required when you aren't applying 100% noise to the masked region, e.g. strength < 1.

* Added strength to check_inputs, throws error if out of range

* Changed `prepare_latents` to initialise latents w.r.t strength

inspired from the stable diffusion img2img pipeline, init latents are initialised by converting the init image into a VAE latent and adding noise (based upon the strength parameter passed in), e.g. random when strength = 1, or the init image at strength = 0.

* WIP: Added a unit test for the new strength parameter in the StableDiffusionInpaintingPipeline

still need to add correct regression values

* Created a is_strength_max to initialise from pure random noise

* Updated unit tests w.r.t new strength parameter + fixed new strength unit test

* renamed parameter to avoid confusion with variable of same name

* Updated regression values for new strength test - now passes

* removed 'copied from' comment as this method is now different and divergent from the cpy

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* Ensure backwards compatibility for prepare_mask_and_masked_image

created a return_image boolean and initialised to false

* Ensure backwards compatibility for prepare_latents

* Fixed copy check typo

* Fixes w.r.t backward compibility changes

* make style

* keep function argument ordering same for backwards compatibility in callees with copied from statements

* make fix-copies

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: default avatarWilliam Berman <WLBberman@gmail.com>
      c09c4f3a
  25. 16 May, 2023 1 commit
    • Patrick von Platen's avatar
      Refactor controlnet and add img2img and inpaint (#3386) · 886575ee
      Patrick von Platen authored 
      * refactor controlnet and add img2img and inpaint

* First draft to get pipelines to work

* make style

* Fix more

* Fix more

* More tests

* Fix more

* Make inpainting work

* make style and more tests

* Apply suggestions from code review

* up

* make style

* Fix imports

* Fix more

* Fix more

* Improve examples

* add test

* Make sure import is correctly deprecated

* Make sure everything works in compile mode

* make sure authorship is correctly attributed
      886575ee
  27. 11 May, 2023 2 commits
    • Sayak Paul's avatar
      [Tests] better determinism (#3374) · 90f5f3c4
      Sayak Paul authored 
      * enable deterministic pytorch and cuda operations.

* disable manual seeding.

* make style && make quality for unet_2d tests.

* enable determinism for the unet2dconditional model.

* add CUBLAS_WORKSPACE_CONFIG for better reproducibility.

* relax tolerance (very weird issue, though).

* revert to torch manual_seed() where needed.

* relax more tolerance.

* better placement of the cuda variable and relax more tolerance.

* enable determinism for 3d condition model.

* relax tolerance.

* add: determinism to alt_diffusion.

* relax tolerance for alt diffusion.

* dance diffusion.

* dance diffusion is flaky.

* test_dict_tuple_outputs_equivalent edit.

* fix two more tests.

* fix more ddim tests.

* fix: argument.

* change to diff in place of difference.

* fix: test_save_load call.

* test_save_load_float16 call.

* fix: expected_max_diff

* fix: paint by example.

* relax tolerance.

* add determinism to 1d unet model.

* torch 2.0 regressions seem to be brutal

* determinism to vae.

* add reason to skipping.

* up tolerance.

* determinism to vq.

* determinism to cuda.

* determinism to the generic test pipeline file.

* refactor general pipelines testing a bit.

* determinism to alt diffusion i2i

* up tolerance for alt diff i2i and audio diff

* up tolerance.

* determinism to audioldm

* increase tolerance for audioldm lms.

* increase tolerance for paint by paint.

* increase tolerance for repaint.

* determinism to cycle diffusion and sd 1.

* relax tol for cycle diffusion 🚲

* relax tol for sd 1.0

* relax tol for controlnet.

* determinism to img var.

* relax tol for img variation.

* tolerance to i2i sd

* make style

* determinism to inpaint.

* relax tolerance for inpaiting.

* determinism for inpainting legacy

* relax tolerance.

* determinism to instruct pix2pix

* determinism to model editing.

* model editing tolerance.

* panorama determinism

* determinism to pix2pix zero.

* determinism to sag.

* sd 2. determinism

* sd. tolerance

* disallow tf32 matmul.

* relax tolerance is all you need.

* make style and determinism to sd 2 depth

* relax tolerance for depth.

* tolerance to diffedit.

* tolerance to sd 2 inpaint.

* up tolerance.

* determinism in upscaling.

* tolerance in upscaler.

* more tolerance relaxation.

* determinism to v pred.

* up tol for v_pred

* unclip determinism

* determinism to unclip img2img

* determinism to text to video.

* determinism to last set of tests

* up tol.

* vq cumsum doesn't have a deterministic kernel

* relax tol

* relax tol
      90f5f3c4
    • Takuma Mori's avatar
      Support ControlNet v1.1 shuffle properly (#3340) · 01c056f0
      Takuma Mori authored 
      

* add inferring_controlnet_cond_batch

* Revert "add inferring_controlnet_cond_batch"

This reverts commit abe8d6311d4b7f5b9409ca709c7fabf80d06c1a9.

* set guess_mode to True
whenever global_pool_conditions is True
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>

* nit

* add integration test

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      01c056f0
  29. 10 May, 2023 2 commits
    • Patrick von Platen's avatar
      make style · 82e6fa56
      Patrick von Platen authored
      82e6fa56
    • Rupert Menneer's avatar
      StableDiffusionInpaintingPipeline - resize image w.r.t height and width (#3322) · edb087a2
      Rupert Menneer authored 
      

* StableDiffusionInpaintingPipeline now resizes input images and masks w.r.t to passed input height and width. Default is already set to 512. This addresses the common tensor mismatch error. Also moved type check into relevant funciton to keep main pipeline body tidy.

* Fixed StableDiffusionInpaintingPrepareMaskAndMaskedImageTests

Due to previous commit these tests were failing as height and width need to be passed into the prepare_mask_and_masked_image function, I have updated the code and added a height/width variable per unit test as it seemed more appropriate than the current hard coded solution

* Added a resolution test to StableDiffusionInpaintPipelineSlowTests

this unit test simply gets the input and resizes it into some that would fail (e.g. would throw a tensor mismatch error/not a mult of 8). Then passes it through the pipeline and verifies it produces output with correct dims w.r.t the passed height and width

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      edb087a2
  31. 09 May, 2023 1 commit
  33. 06 May, 2023 1 commit
  35. 02 May, 2023 1 commit
  37. 01 May, 2023 2 commits
  39. 20 Apr, 2023 1 commit
  41. 19 Apr, 2023 2 commits
    • hwuebben's avatar
      Update pipeline_stable_diffusion_inpaint_legacy.py (#2903) · 3becd368
      hwuebben authored 
      

* Update pipeline_stable_diffusion_inpaint_legacy.py

* fix preprocessing of Pil images with adequate batch size

* revert map

* add tests

* reformat

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* next try to fix the style

* wth is this

* Update testing_utils.py

* Update testing_utils.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      3becd368
    • 1lint's avatar
      add from_ckpt method as Mixin (#2318) · 86ecd4b7
      1lint authored 
      

* add mixin class for pipeline from original sd ckpt

* Improve

* make style

* merge main into

* Improve more

* fix more

* up

* Apply suggestions from code review

* finish docs

* rename

* make style

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      86ecd4b7
  43. 17 Apr, 2023 2 commits
  45. 14 Apr, 2023 1 commit
  47. 13 Apr, 2023 1 commit
  49. 12 Apr, 2023 2 commits
  51. 11 Apr, 2023 1 commit
    • Chanchana Sornsoontorn's avatar
      Fix typo and format BasicTransformerBlock attributes (#2953) · 52c4d32d
      Chanchana Sornsoontorn authored 
      * ⚙️chore(train_controlnet) fix typo in logger message

* ⚙️chore(models) refactor modules order; make them the same as calling order

When printing the BasicTransformerBlock to stdout, I think it's crucial that the attributes order are shown in proper order. And also previously the "3. Feed Forward" comment was not making sense. It should have been close to self.ff but it's instead next to self.norm3

* correct many tests

* remove bogus file

* make style

* correct more tests

* finish tests

* fix one more

* make style

* make unclip deterministic

* ⚙

️chore(models/attention) reorganize comments in BasicTransformerBlock class

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      52c4d32d
  53. 31 Mar, 2023 2 commits
  55. 30 Mar, 2023 1 commit
  57. 28 Mar, 2023 1 commit