Skip to content

GitLab

Switch branch/tag
  1. 24 May, 2024 2 commits
    • Yue Wu's avatar
      sampling bug fix in diffusers tutorial "basic_training.md" (#8223) · 1096f88e
      Yue Wu authored 
      sampling bug fix in basic_training.md

In the diffusers basic training tutorial, setting the manual seed argument (generator=torch.manual_seed(config.seed)) in the pipeline call inside evaluate() function rewinds the dataloader shuffling, leading to overfitting due to the model seeing same sequence of training examples after every evaluation call. Using generator=torch.Generator(device='cpu').manual_seed(config.seed) avoids this.
      1096f88e
    • Dhruv Nair's avatar
      Clean up `from_single_file` docs (#8268) · cef4a512
      Dhruv Nair authored 
      * update

* update
      cef4a512
  3. 21 May, 2024 1 commit
  5. 20 May, 2024 2 commits
  7. 13 May, 2024 1 commit
  9. 10 May, 2024 4 commits
    • 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
    • Sayak Paul's avatar
      [Core] introduce videoprocessor. (#7776) · 04f4bd54
      Sayak Paul authored 
      

* introduce videoprocessor.

* fix quality

* address yiyi's feedback

* fix preprocess_video call.

* video_processor -> image_processor

* fix

* fix more.

* quality

* image_processor -> video_processor

* support List[List[PIL.Image.Image]]

* change to video_processor.

* documentation

* Apply suggestions from code review

* changes

* remove print.

* refactor video processor (part # 7776) (#7861)

* update

* update remove deprecate

* Update src/diffusers/video_processor.py

* update

* Apply suggestions from code review

* deprecate list of 5d for video and list of 4d for image + apply other feedbacks

* up

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

* add doc.

* tensor2vid -> postprocess_video.

* refactor preprocess with preprocess_video

* set default values.

* empty commit

* more refactoring of prepare_latents in animatediff vid2vid

* checking documentation

* remove documentation for now.

* fix animatediff sdxl

* fix test failure [part of video processor PR] (#7905)

up

* remove preceed_with_frames.

* doc

* fix

* fix

* remove video input as a single-frame video.

---------
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
      04f4bd54
    • Sayak Paul's avatar
      add missing image processors to the docs (#7910) · 82be58c5
      Sayak Paul authored 
      add missing processors.
      82be58c5
    • Sayak Paul's avatar
      upgrade to python 3.10 in the Dockerfiles (#7893) · 66956356
      Sayak Paul authored 
      * upgrade to python 3.10

* fix

* try https://askubuntu.com/questions/1459694/can-not-find-python3-10-after-apt-get-installation

* fix

* up

* yes

* okay

* up

* up

* up

* up

* up

* check

* okay

* up

* i[

* fix
      66956356
  11. 09 May, 2024 2 commits
  13. 08 May, 2024 1 commit
    • Aryan's avatar
      [Pipeline] AnimateDiff SDXL (#6721) · 818f7607
      Aryan authored 
      

* update conversion script to handle motion adapter sdxl checkpoint

* add animatediff xl

* handle addition_embed_type

* fix output

* update

* add imports

* make fix-copies

* add decode latents

* update docstrings

* add animatediff sdxl to docs

* remove unnecessary lines

* update example

* add test

* revert conv_in conv_out kernel param

* remove unused param addition_embed_type_num_heads

* latest IPAdapter impl

* make fix-copies

* fix return

* add IPAdapterTesterMixin to tests

* fix return

* revert based on suggestion

* add freeinit

* fix test_to_dtype test

* use StableDiffusionMixin instead of different helper methods

* fix progress bar iterations

* apply suggestions from review

* hardcode flip_sin_to_cos and freq_shift

* make fix-copies

* fix ip adapter implementation

* fix last failing test

* make style

* Update docs/source/en/api/pipelines/animatediff.md
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>

* remove todo

* fix doc-builder errors

---------
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
      818f7607
  15. 07 May, 2024 1 commit
  17. 06 May, 2024 1 commit
  19. 03 May, 2024 2 commits
  21. 30 Apr, 2024 1 commit
  23. 28 Apr, 2024 1 commit
  25. 26 Apr, 2024 1 commit
  27. 25 Apr, 2024 2 commits
  29. 23 Apr, 2024 1 commit
  31. 22 Apr, 2024 2 commits
  33. 19 Apr, 2024 1 commit
  35. 17 Apr, 2024 3 commits
  37. 16 Apr, 2024 1 commit
    • UmerHA's avatar
      Fixing implementation of ControlNet-XS (#6772) · fda1531d
      UmerHA authored 
      

* CheckIn - created DownSubBlocks

* Added extra channels, implemented subblock fwd

* Fixed connection sizes

* checkin

* Removed iter, next in forward

* Models for SD21 & SDXL run through

* Added back pipelines, cleared up connections

* Cleaned up connection creation

* added debug logs

* updated logs

* logs: added input loading

* Update umer_debug_logger.py

* log: Loading hint

* Update umer_debug_logger.py

* added logs

* Changed debug logging

* debug: added more logs

* Fixed num_norm_groups

* Debug: Logging all of SDXL input

* Update umer_debug_logger.py

* debug: updated logs

* checkim

* Readded tests

* Removed debug logs

* Fixed Slow Tests

* Added value ckecks | Updated model_cpu_offload_seq

* accelerate-offloading works ; fast tests work

* Made unet & addon explicit in controlnet

* Updated slow tests

* Added dtype/device to ControlNetXS

* Filled in test model paths

* Added image_encoder/feature_extractor to XL pipe

* Fixed fast tests

* Added comments and docstrings

* Fixed copies

* Added docs ; Updates slow tests

* Moved changes to UNetMidBlock2DCrossAttn

* tiny cleanups

* Removed stray prints

* Removed ip adapters + freeU

- Removed ip adapters + freeU as they don't make sense for ControlNet-XS
- Fixed imports of UNet components

* Fixed test_save_load_float16

* Make style, quality, fix-copies

* Changed loading/saving API for ControlNetXS

- Changed loading/saving API for ControlNetXS
- other small fixes

* Removed ControlNet-XS from research examples

* Make style, quality, fix-copies

* Small fixes

- deleted ControlNetXSModel.init_original
- added time_embedding_mix to StableDiffusionControlNetXSPipeline .from_pretrained / StableDiffusionXLControlNetXSPipeline.from_pretrained
- fixed copy hints

* checkin May 11 '23

* CheckIn Mar 12 '24

* Fixed tests for SD

* Added tests for UNetControlNetXSModel

* Fixed SDXL tests

* cleanup

* Delete Pipfile

* CheckIn Mar 20

Started replacing sub blocks  by `ControlNetXSCrossAttnDownBlock2D` and `ControlNetXSCrossAttnUplock2D`

* check-in Mar 23

* checkin 24 Mar

* Created init for UNetCnxs and CnxsAddon

* CheckIn

* Made from_modules, from_unet and no_control work

* make style,quality,fix-copies & small changes

* Fixed freezing

* Added gradient ckpt'ing; fixed tests

* Fix slow tests(+compile) ; clear naming confusion

* Don't create UNet in init ; removed class_emb

* Incorporated review feedback

- Deleted get_base_pipeline /  get_controlnet_addon for pipes
- Pipes inherit from StableDiffusionXLPipeline
- Made module dicts for cnxs-addon's down/mid/up classes
- Added support for qkv fusion and freeU

* Make style, quality, fix-copies

* Implemented review feedback

* Removed compatibility check for vae/ctrl embedding

* make style, quality, fix-copies

* Delete Pipfile

* Integrated review feedback

- Importing ControlNetConditioningEmbedding now
- get_down/mid/up_block_addon now outside class
- renamed `do_control` to `apply_control`

* Reduced size of test tensors

For this, added `norm_num_groups` as parameter everywhere

* Renamed cnxs-`Addon` to cnxs-`Adapter`

- `ControlNetXSAddon` -> `ControlNetXSAdapter`
- `ControlNetXSAddonDownBlockComponents` -> `DownBlockControlNetXSAdapter`, and similarly for mid/up
- `get_mid_block_addon` -> `get_mid_block_adapter`, and similarly for mid/up

* Fixed save_pretrained/from_pretrained bug

* Removed redundant code

---------
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
      fda1531d
  39. 11 Apr, 2024 1 commit
  41. 10 Apr, 2024 3 commits
    • Steven Liu's avatar
      [docs] Prompt enhancer (#7565) · 1d480298
      Steven Liu authored 
      * prompt enhance

* edits

* align titles

* feedback

* feedback

* feedback

* link to style
      1d480298
    • Sayak Paul's avatar
      [docs] remove duplicate tip block. (#7625) · a402431d
      Sayak Paul authored 
      remove duplicate tip block.
      a402431d
    • Sayak Paul's avatar
      [Core] add "balanced" `device_map` support to pipelines (#6857) · 3e4a6bd2
      Sayak Paul authored 
      

* get device <-> component mapping when using multiple gpus.

* condition the device_map bits.

* relax condition

* device_map progress.

* device_map enhancement

* some cleaning up and debugging

* Apply suggestions from code review
Co-authored-by: default avatarMarc Sun <57196510+SunMarc@users.noreply.github.com>

* incorporate suggestions from PR.

* remove multi-gpu condition for now.

* guard check the component -> device mapping

* fix: device_memory variable

* dispatching transformers model to have force_hooks=True

* better guarding for transformers device_map

* introduce support balanced_low_memory and balanced_ultra_low_memory.

* remove device_map patch.

* fix: intermediate variable scoping.

* fix: condition in cpu offload.

* fix: flax class restrictions.

* remove modifications from cpu_offload and model_offload

* incorporate changes.

* add a simple forward pass test

* add: torch_device in get_inputs()

* add: tests

* remove print

* safe-guard to(), model offloading and cpu offloading when balanced is used as a device_map.

* style

* remove .

* safeguard device_map with more checks and remove invalid device_mapping strategues.

* make  a class attribute and adjust tests accordingly.

* fix device_map check

* fix test

* adjust comment

* fix: device_map attribute

* fix: dispatching.

* max_memory test for pipeline

* version guard the tests

* fix guard.

* address review feedback.

* reset_device_map method.

* add: test for reset_hf_device_map

* fix a couple things.

* add reset_device_map() in the error message.

* add tests for checking reset_device_map doesn't have unintended consequences.

* fix reset_device_map and offloading tests.

* create _get_final_device_map utility.

* hf_device_map -> _hf_device_map

* add documentation

* add notes suggested by Marc.

* styling.

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

* move updates within gpu condition.

* other docs related things

* note on ignore a device not specified in .

* provide a suggestion if device mapping errors out.

* fix: typo.

* _hf_device_map -> hf_device_map

* Empty-Commit

* add: example hf_device_map.

---------
Co-authored-by: default avatarMarc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
      3e4a6bd2
  43. 08 Apr, 2024 2 commits
  45. 01 Apr, 2024 1 commit
  47. 29 Mar, 2024 1 commit
    • UmerHA's avatar
      Implements Blockwise lora (#7352) · 03024468
      UmerHA authored 
      

* Initial commit

* Implemented block lora

- implemented block lora
- updated docs
- added tests

* Finishing up

* Reverted unrelated changes made by make style

* Fixed typo

* Fixed bug + Made text_encoder_2 scalable

* Integrated some review feedback

* Incorporated review feedback

* Fix tests

* Made every module configurable

* Adapter to new lora test structure

* Final cleanup

* Some more final fixes

- Included examples in `using_peft_for_inference.md`
- Added hint that only attns are scaled
- Removed NoneTypes
- Added test to check mismatching lens of adapter names / weights raise error

* Update using_peft_for_inference.md

* Update using_peft_for_inference.md

* Make style, quality, fix-copies

* Updated tutorial;Warning if scale/adapter mismatch

* floats are forwarded as-is; changed tutorial scale

* make style, quality, fix-copies

* Fixed typo in tutorial

* Moved some warnings into `lora_loader_utils.py`

* Moved scale/lora mismatch warnings back

* Integrated final review suggestions

* Empty commit to trigger CI

* Reverted emoty commit to trigger CI

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      03024468
  49. 25 Mar, 2024 1 commit
  51. 22 Mar, 2024 1 commit