Skip to content

GitLab

Switch branch/tag
  1. 12 Jun, 2024 1 commit
  3. 05 Jun, 2024 1 commit
  5. 29 May, 2024 1 commit
  7. 24 May, 2024 1 commit
  9. 16 May, 2024 1 commit
  11. 10 May, 2024 1 commit
    • Mark Van Aken's avatar
      #7535 Update FloatTensor type hints to Tensor (#7883) · be4afa0b
      Mark Van Aken authored 
      * find & replace all FloatTensors to Tensor

* apply formatting

* Update torch.FloatTensor to torch.Tensor in the remaining files

* formatting

* Fix the rest of the places where FloatTensor is used as well as in documentation

* formatting

* Update new file from FloatTensor to Tensor
      be4afa0b
  13. 09 May, 2024 2 commits
  15. 08 May, 2024 1 commit
    • Philip Pham's avatar
      Check shape and remove deprecated APIs in scheduling_ddpm_flax.py (#7703) · f29b9348
      Philip Pham authored 
      `model_output.shape` may only have rank 1.

There are warnings related to use of random keys.

```
tests/schedulers/test_scheduler_flax.py: 13 warnings
  /Users/phillypham/diffusers/src/diffusers/schedulers/scheduling_ddpm_flax.py:268: FutureWarning: normal accepts a single key, but was given a key array of shape (1, 2) != (). Use jax.vmap for batching. In a future JAX version, this will be an error.
    noise = jax.random.normal(split_key, shape=model_output.shape, dtype=self.dtype)

tests/schedulers/test_scheduler_flax.py::FlaxDDPMSchedulerTest::test_betas
  /Users/phillypham/virtualenv/diffusers/lib/python3.9/site-packages/jax/_src/random.py:731: FutureWarning: uniform accepts a single key, but was given a key array of shape (1,) != (). Use jax.vmap for batching. In a future JAX version, this will be an error.
    u = uniform(key, shape, dtype, lo, hi)  # type: ignore[arg-type]
```
      f29b9348
  17. 03 May, 2024 1 commit
  19. 29 Apr, 2024 1 commit
  21. 27 Apr, 2024 1 commit
  23. 03 Apr, 2024 2 commits
    • Beinsezii's avatar
      UniPC Multistep add `rescale_betas_zero_snr` (#7531) · aa190259
      Beinsezii authored 
      * UniPC Multistep add `rescale_betas_zero_snr`

Same patch as DPM and Euler with the patched final alpha cumprod

BF16 doesn't seem to break down, I think cause UniPC upcasts during some
phases already? We could still force an upcast since it only
loses ≈ 0.005 it/s for me but the difference in output is very small. A
better endeavor might upcasting in step() and removing all the other
upcasts elsewhere?

* UniPC ZSNR UT

* Re-add `rescale_betas_zsnr` doc oops
      aa190259
    • Beinsezii's avatar
      UniPC Multistep fix tensor dtype/device on order=3 (#7532) · 19ab04ff
      Beinsezii authored 
      * UniPC UTs iterate solvers on FP16

It wasn't catching errs on order==3. Might be excessive?

* UniPC Multistep fix tensor dtype/device on order=3

* UniPC UTs Add v_pred to fp16 test iter

For completions sake. Probably overkill?
      19ab04ff
  25. 02 Apr, 2024 1 commit
    • Sayak Paul's avatar
      add: utility to format our docs too 📜 (#7314) · 4a343077
      Sayak Paul authored 
      * add: utility to format our docs too 📜

* debugging saga

* fix: message

* checking

* should be fixed.

* revert pipeline_fixture

* remove empty line

* make style

* fix: setup.py

* style.
      4a343077
  27. 30 Mar, 2024 1 commit
    • Beinsezii's avatar
      Add `final_sigma_zero` to UniPCMultistep (#7517) · f0c81562
      Beinsezii authored 
      * Add `final_sigma_zero` to UniPCMultistep

Effectively the same trick as DDIM's `set_alpha_to_one` and
DPM's `final_sigma_type='zero'`.
Currently False by default but maybe this should be True?

* `final_sigma_zero: bool` -> `final_sigmas_type: str`

Should 1:1 match DPM Multistep now.

* Set `final_sigmas_type='sigma_min'` in UniPC UTs
      f0c81562
  29. 21 Mar, 2024 1 commit
  31. 19 Mar, 2024 2 commits
  33. 18 Mar, 2024 2 commits
    • M. Tolga Cangöz's avatar
      Update access of configuration attributes (#7343) · e97a633b
      M. Tolga Cangöz authored 
      
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      e97a633b
    • M. Tolga Cangöz's avatar
      Fix Typos (#7325) · 6a05b274
      M. Tolga Cangöz authored 
      * Fix PyTorch's convention for inplace functions

* Fix import structure in __init__.py and update config loading logic in test_config.py

* Update configuration access

* Fix typos

* Trim trailing white spaces

* Fix typo in logger name

* Revert "Fix PyTorch's convention for inplace functions"

This reverts commit f65dc4afcb57ceb43d5d06389229d47bafb10d2d.

* Fix typo in step_index property description

* Revert "Update configuration access"

This reverts commit 8d44e870b8c1ad08802e3e904c34baeca1b598f8.

* Revert "Fix import structure in __init__.py and update config loading logic in test_config.py"

This reverts commit 2ad5e8bca25aede3b912da22bd57285b598fe171.

* Fix typos

* Fix typos

* Fix typos

* Fix a typo: tranform -> transform
      6a05b274
  35. 14 Mar, 2024 2 commits
  37. 13 Mar, 2024 2 commits
    • Manuel Brack's avatar
      [Pipeline] Add LEDITS++ pipelines (#6074) · 00eca4b8
      Manuel Brack authored 
      

* Setup LEdits++ file structure

* Fix import

* LEditsPP Stable Diffusion pipeline

* Include variable image aspect ratios

* Implement LEDITS++ for SDXL

* clean up LEditsPPPipelineStableDiffusion

* Adjust inversion output

* Added docu, more cleanup for LEditsPPPipelineStableDiffusion

* clean up LEditsPPPipelineStableDiffusionXL

* Update documentation

* Fix documentation import

* Add skeleton IF implementation

* Fix documentation typo

* Add LEDTIS docu to toctree

* Add missing title

* Finalize SD documentation

* Finalize SD-XL documentation

* Fix code style and quality

* Fix typo

* Fix return types

* added LEditsPPPipelineIF; minor changes for LEditsPPPipelineStableDiffusion and LEditsPPPipelineStableDiffusionXL

* Fix copy reference

* add documentation for IF

* Add first tests

* Fix batching for SD-XL

* Fix text encoding and perfect reconstruction for SD-XL

* Add tests for SD-XL, minor changes

* move user_mask to correct device, use cross_attention_kwargs also for inversion

* Example docstring

* Fix attention resolution for non-square images

* Refactoring for PR review

* Safely remove ledits_utils.py

* Style fixes

* Replace assertions with ValueError

* Remove LEditsPPPipelineIF

* Remove unecessary input checks

* Refactoring of CrossAttnProcessor

* Revert unecessary changes to scheduler

* Remove first progress-bar in inversion

* Refactor scheduler usage and reset

* Use imageprocessor instead of custom logic

* Fix scheduler init warning

* Fix error when running the pipeline in fp16

* Update documentation wrt perfect inversion

* Update tests

* Fix code quality and copy consistency

* Update LEditsPP import

* Remove enable/disable methods that are now in StableDiffusionMixin

* Change import in docs

* Revert import structure change

* Fix ledits imports

---------
Co-authored-by: default avatarKatharina Kornmeier <katharina.kornmeier@stud.tu-darmstadt.de>
      00eca4b8
    • Sayak Paul's avatar
      [Chore] switch to `logger.warning` (#7289) · 4fbd310f
      Sayak Paul authored 
      switch to logger.warning
      4fbd310f
  39. 08 Mar, 2024 1 commit
    • Chi's avatar
      Solve missing clip_sample implementation in FlaxDDIMScheduler. (#7017) · 46fac824
      Chi authored 
      

* I added a new doc string to the class. This is more flexible to understanding other developers what are doing and where it's using.

* Update src/diffusers/models/unet_2d_blocks.py

This changes suggest by maintener.
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* Update src/diffusers/models/unet_2d_blocks.py

Add suggested text
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* Update unet_2d_blocks.py

I changed the Parameter to Args text.

* Update unet_2d_blocks.py

proper indentation set in this file.

* Update unet_2d_blocks.py

a little bit of change in the act_fun argument line.

* I run the black command to reformat style in the code

* Update unet_2d_blocks.py

similar doc-string add to have in the original diffusion repository.

* Fix bug for mention in this issue section #6901

* Update src/diffusers/schedulers/scheduling_ddim_flax.py
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>

* Fix linter

* Restore empty line

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
      46fac824
  41. 05 Mar, 2024 1 commit
  43. 04 Mar, 2024 1 commit
    • Thiago Crepaldi's avatar
      Enable PyTorch's FakeTensorMode for EulerDiscreteScheduler scheduler (#7151) · ca6cdc77
      Thiago Crepaldi authored 
      * Enable FakeTensorMode for EulerDiscreteScheduler scheduler

PyTorch's FakeTensorMode does not support `.numpy()` or `numpy.array()`
calls.

This PR replaces `sigmas` numpy tensor by a PyTorch tensor equivalent

Repro

```python
with torch._subclasses.FakeTensorMode() as fake_mode, ONNXTorchPatcher():
    fake_model = DiffusionPipeline.from_pretrained(model_name, low_cpu_mem_usage=False)
```

that otherwise would fail with
`RuntimeError: .numpy() is not supported for tensor subclasses.`

* Address comments
      ca6cdc77
  45. 27 Feb, 2024 3 commits
  47. 13 Feb, 2024 1 commit
  49. 08 Feb, 2024 1 commit
  51. 01 Feb, 2024 1 commit
  53. 31 Jan, 2024 1 commit
  55. 30 Jan, 2024 1 commit
  57. 26 Jan, 2024 1 commit
  59. 22 Jan, 2024 1 commit
  61. 19 Jan, 2024 1 commit
  63. 28 Dec, 2023 1 commit