Skip to content

GitLab

Switch branch/tag
  1. 30 Oct, 2023 3 commits
  3. 27 Oct, 2023 1 commit
  5. 26 Oct, 2023 1 commit
  7. 25 Oct, 2023 4 commits
  9. 24 Oct, 2023 2 commits
    • dg845's avatar
      Add Latent Consistency Models Pipeline (#5448) · 958e17da
      dg845 authored 
      

* initial commit for LatentConsistencyModelPipeline and LCMScheduler based on the community pipeline

* Add callback and freeu support.

* apply suggestions from review

* Clean up LCMScheduler

* Remove timeindex argument to LCMScheduler.step.

* Add support for clipping or thresholding the predicted original sample.

* Remove unused methods and arguments in LCMScheduler.

* Improve comment about (lack of) negative prompt support.

* Change input guidance_scale to match the StableDiffusionPipeline (Imagen) CFG formulation.

* Move lcm_origin_steps from pipeline __call__ to LCMScheduler.__init__/config (as origin_steps).

* Fix typo when clipping/thresholding in LCMScheduler.

* Add some initial LCMScheduler tests.

* add type annotations from review

* Fix type annotation bug.

* Override test_add_noise_device in LCMSchedulerTest since hardcoded timesteps doesn't work under default settings.

* Add generator argument pipeline prepare_latents call.

* Cast LCMScheduler.timesteps to long in set_timesteps.

* Add onestep and multistep full loop scheduler tests.

* Set default height/width to None and don't hardcode guidance scale embedding dim.

* Add initial LatentConsistencyPipeline fast and slow tests.

* Add initial documentation for LatentConsistencyModelPipeline and LCMScheduler.

* Make remaining failing fast tests pass.

* make style

* Make original_inference_steps configurable from pipeline __call__ again.

* make style

* Remove guidance_rescale arg from pipeline __call__ since LCM currently doesn't support CFG.

* Make LCMScheduler defaults match config of LCM_Dreamshaper_v7 checkpoint.

* Fix LatentConsistencyPipeline slow tests and add dummy expected slices.

* Add checks for original_steps in LCMScheduler.set_timesteps.

* make fix-copies

* Improve LatentConsistencyModelPipeline docs.

* Apply suggestions from code review
Co-authored-by: default avatarAryan V S <avs050602@gmail.com>

* Apply suggestions from code review
Co-authored-by: default avatarAryan V S <avs050602@gmail.com>

* Apply suggestions from code review
Co-authored-by: default avatarAryan V S <avs050602@gmail.com>

* Update src/diffusers/schedulers/scheduling_lcm.py

* Apply suggestions from code review
Co-authored-by: default avatarAryan V S <avs050602@gmail.com>

* finish

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: default avatarAryan V S <avs050602@gmail.com>
      958e17da
    • Sayak Paul's avatar
      [Core] Refactor activation and normalization layers (#5493) · 77241c48
      Sayak Paul authored 
      

* move out the activations.

* move normalization layers.

* add doc.

* add doc.

* fix: paths

* Apply suggestions from code review
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>

* style

---------
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
      77241c48
  11. 23 Oct, 2023 3 commits
  13. 21 Oct, 2023 1 commit
  15. 20 Oct, 2023 1 commit
    • Vishnu V Jaddipal's avatar
      Added support to create asymmetrical U-Net structures (#5400) · 8dba1808
      Vishnu V Jaddipal authored 
      

* Added args, kwargs to ```U

* Add UNetMidBlock2D as a supported mid block type

* Fix extra init input for UNetMidBlock2D, change allowed types for Mid-block init

* Update unet_2d_condition.py

* Update unet_2d_condition.py

* Update unet_2d_condition.py

* Update unet_2d_condition.py

* Update unet_2d_condition.py

* Update unet_2d_condition.py

* Update unet_2d_condition.py

* Update unet_2d_condition.py

* Update unet_2d_blocks.py

* Update unet_2d_blocks.py

* Update unet_2d_blocks.py

* Update unet_2d_condition.py

* Update unet_2d_blocks.py

* Updated docstring, increased check strictness

Updated the docstring for ```UNet2DConditionModel``` to include ```reverse_transformer_layers_per_block``` and updated checking for nested list type ```transformer_layers_per_block```

* Add basic shape-check test for asymmetrical unets

* Update src/diffusers/models/unet_2d_blocks.py

Removed blank line
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* Update unet_2d_condition.py

Remove blank space

* Update unet_2d_condition.py

Changed docstring for `mid_block_type`

* Fixed docstring and wrong default value

* Reformat with black

* Reformat with necessary commands

* Add UNetMidBlockFlat to versatile_diffusion/modeling_text_unet.py to ensure consistency

* Removed args, kwargs, use on mid-block type

* Make fix-copies

* Update src/diffusers/models/unet_2d_condition.py

Wrap into single line
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* make fix-copies

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      8dba1808
  17. 18 Oct, 2023 4 commits
  19. 17 Oct, 2023 1 commit
    • Sayak Paul's avatar
      [Core] Fix/pipeline without text encoders for SDXL (#5301) · 8b3d2aea
      Sayak Paul authored 
      

* fix: sdxl pipeline when unet is not available.

* fix moe

* account for text

* ifx more

* don't make unet optional.

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

* split conditionals.

* add optional components to sdxl pipeline

* propagate changes to the rest of the pipelines.

* add: test

* add to all

* fix: rest of the pipelines.

* use pipeline_class variable

* separate pipeline mixin

* use safe_serialization

* fix: test

* access actual output.

* add: optional test to adapter and ip2p sdxl pipeline tests/

* add optional test to controlnet sdxl.

* fix tests

* fix ip2p tests

* fix more

* fifx more.

* use np output type.

* fix for StableDiffusionXLMultiControlNetPipelineFastTests.

* fix: SDXLOptionalComponentsTesterMixin

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

* fix tests

* Empty-Commit

* revert previous

* quality

* fix: test

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      8b3d2aea
  21. 16 Oct, 2023 4 commits
  23. 13 Oct, 2023 2 commits
  25. 11 Oct, 2023 1 commit
  27. 09 Oct, 2023 5 commits
  29. 06 Oct, 2023 2 commits
    • vedant2003's avatar
      [Hacktoberfest]Fixing issues #5241 (#5255) · dd25ef56
      vedant2003 authored 
      

* Update pipeline_wuerstchen_prior.py

* prior_num_inference_steps updated

* height, width, num_inference_steps, and guidance_scale synced

* parameters synced

* latent_mean, latent_std, and resolution_multiple synced

* prior_num_inference_steps changed

* Formatted pipeline_wuerstchen_prior.py

* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_prior.py

---------
Co-authored-by: default avatarKashif Rasul <kashif.rasul@gmail.com>
      dd25ef56
    • Dhruv Nair's avatar
      Add from single file to StableDiffusionUpscalePipeline and... · 872ae1dd
      Dhruv Nair authored 
      Add from single file to StableDiffusionUpscalePipeline and StableDiffusionLatentUpscalePipeline (#5194)

* add from single file

* clean up

* make style

* add single file loading for upscaling
      872ae1dd
  31. 05 Oct, 2023 1 commit
    • Kadir Nar's avatar
      ✨ [Core] Add FreeU mechanism (#5164) · 84b82a6c
      Kadir Nar authored 
      * ✨ Added Fourier filter function to upsample blocks

* 🔧 Update Fourier_filter for float16 support

* ✨ Added UNetFreeUConfig to UNet model for FreeU adaptation 🛠

️

* move unet to its original form and add fourier_filter to torch_utils.

* implement freeU enable mechanism

* implement disable mechanism

* resolution index.

* correct resolution idx condition.

* fix copies.

* no need to use resolution_idx in vae.

* spell out the kwargs

* proper config property

* fix attribution setting

* place unet hasattr properly.

* fix: attribute access.

* proper disable

* remove validation method.

* debug

* debug

* debug

* debug

* debug

* debug

* potential fix.

* add: doc.

* fix copies

* add: tests.

* add: support freeU in SDXL.

* set default value of resolution idx.

* set default values for resolution_idx.

* fix copies

* fix rest.

* fix copies

* address PR comments.

* run fix-copies

* move apply_free_u to utils and other minors.

* introduce support for video (unet3D)

* minor ups

* consistent fix-copies.

* consistent stuff

* fix-copies

* add: rest

* add: docs.

* fix: tests

* fix: doc path

* Apply suggestions from code review
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>

* style up

* move to techniques.

* add: slow test for sd freeu.

* add: slow test for sd freeu.

* add: slow test for sd freeu.

* add: slow test for sd freeu.

* add: slow test for sd freeu.

* add: slow test for sd freeu.

* add: slow test for video with freeu

* add: slow test for video with freeu

* add: slow test for video with freeu

* style

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
      84b82a6c
  33. 04 Oct, 2023 1 commit
    • Dhruv Nair's avatar
      New Pipeline Slow Test runners (#5131) · dd5a3629
      Dhruv Nair authored 
      

* pipline fetcher

* update script

* clean up

* clean up

* clean up

* new pipeline runner

* rename tests to match modules

* test actions in pr

* change runner to gpu

* clean up

* clean up

* clean up

* fix report

* fix reporting

* clean up

* show test stats in failure reports

* give names to jobs

* add lora tests

* split torch cuda tests and add compile tests

* clean up

* fix tests

* change push to run only on main

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      dd5a3629
  35. 02 Oct, 2023 3 commits
    • Patrick von Platen's avatar
      [Schedulers] Fix callback steps (#5261) · bdd16116
      Patrick von Platen authored 
      * fix all

* make fix copies

* make fix copies
      bdd16116
    • dg845's avatar
      [WIP] Refactor UniDiffuser Pipeline and Tests (#4948) · cd1b8d7c
      dg845 authored 
      

* Add VAE slicing and tiling methods.

* Switch to using VaeImageProcessing for preprocessing and postprocessing of images.

* Rename the VaeImageProcessor to vae_image_processor to avoid a name clash with the CLIPImageProcessor (image_processor).

* Remove the postprocess() function because we're using a VaeImageProcessor instead.

* Remove UniDiffuserPipeline.decode_image_latents because we're using VaeImageProcessor instead.

* Refactor generating text from text latents into a decode_text_latents method.

* Add enable_full_determinism() to UniDiffuser tests.

* make style

* Add PipelineLatentTesterMixin to UniDiffuserPipelineFastTests.

* Remove enable_model_cpu_offload since it is now part of DiffusionPipeline.

* Rename the VaeImageProcessor instance to self.image_processor for consistency with other pipelines and rename the CLIPImageProcessor instance to clip_image_processor to avoid a name clash.

* Update UniDiffuser conversion script.

* Make safe_serialization configurable in UniDiffuser conversion script.

* Rename image_processor to clip_image_processor in UniDiffuser tests.

* Add PipelineKarrasSchedulerTesterMixin to UniDiffuserPipelineFastTests.

* Add initial test for compiling the UniDiffuser model (not tested yet).

* Update encode_prompt and _encode_prompt to match that of StableDiffusionPipeline.

* Turn off standard classifier-free guidance for now.

* make style

* make fix-copies

* apply suggestions from review

---------
Co-authored-by: default avatarPatrick von Platen <patrick.v.platen@gmail.com>
      cd1b8d7c
    • Pedro Cuenca's avatar
      Flax: Ignore PyTorch, ONNX files when they coexist with Flax weights (#5237) · 0c7cb9a6
      Pedro Cuenca authored 
      Ignore PyTorch, ONNX files when they coexist with Flax weights
      0c7cb9a6