AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-27 17:22:53 +03:00
Code Activity
3,260 Commits 740 Branches 94 Tags
81780882b8cfb7628a2e09dbaae566ead5d760e8
Commit Graph

3260 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Aryan V S
81780882b8 Addition of new callbacks to controlnets (#5812) 
* add new callbacks to src/diffusers/pipelines/controlnet/pipeline_controlnet.py

* update callbacks

* fix repeated kwarg

* update

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-11-21 15:22:20 +01:00
Dhruv Nair
ebc7bedeb7 Add tests fetcher (#5848) 
* add tests fetcher to utils

* add test fetcher

* update

* update

* remove unused dependency version check script

* update

* fix mistake

* update

* update

* update

* update

* update

* update

* update

* remove concurrency params

* update

* update

* update

* update

* update

* update

* move test fetcher to dedicated workflow
 2023-11-21 18:01:44 +05:30
co63oc
ee519cfef5 Update README.md (#5855) 2023-11-21 11:56:13 +01:00
Steven Liu
7457aa67cb [docs] Loader APIs (#5813) 
* first draft

* remove old loader doc

* start adding lora code examples

* finish

* add link to loralinearlayer

* feedback

* fix
 2023-11-20 10:53:13 -08:00
M. Tolga Cangöz
c72a173906 Revert "[Docs] Update and make improvements" (#5858) 
* Revert "[`Docs`] Update and make improvements (#5819)"

This reverts commit c697f52476.

* Update README.md

* Update memory.md

* Update basic_training.md

* Update write_own_pipeline.md

* Update fp16.md

* Update basic_training.md

* Update write_own_pipeline.md

* Update write_own_pipeline.md
 2023-11-20 10:22:21 -08:00
dg845
dc21498b43 Update LCMScheduler Inference Timesteps to be More Evenly Spaced (#5836) 
* Change LCMScheduler.set_timesteps to pick more evenly spaced inference timesteps.

* Change inference_indices implementation to better match previous behavior.

* Add num_inference_steps=26 test case to test_inference_steps.

* run CI

---------

Co-authored-by: patil-suraj <surajp815@gmail.com>
 2023-11-20 15:46:10 +01:00
Patrick von Platen
3303aec5f8 make style 2023-11-20 12:54:52 +01:00
ginjia
4abbbff618 fix an issue that ipex occupy too much memory, it will not impact per… (#5625) 
* fix an issue that ipex occupy too much memory, it will not impact performance

* make style

---------

Co-authored-by: root <jun.chen@intel.com>
Co-authored-by: Meng Guoqing <guoqing.meng@intel.com>
 2023-11-20 12:43:29 +01:00
Younes Belkada
fda297703f [test / peft] Fix silent behaviour on PR tests (#5852) 
Update pr_test_peft_backend.yml
 2023-11-20 12:42:58 +01:00
Roy Hvaara
2695ba8e9d [JAX] Replace uses of jax.devices("cpu") with jax.local_devices(backend="cpu") (#5864) 
An upcoming change to JAX will include non-local (addressable) CPU devices in jax.devices() when JAX is used multicontroller-style, where there are multiple Python processes.

This change preserves the current behavior by replacing uses of jax.devices("cpu"), which previously only returned local devices, with jax.local_devices("cpu"), which will return local devices both now and in the future.

This change is always safe (i.e., it should always preserve the previous behavior), but it may sometimes be unnecessary if code is never used in a multicontroller setting.

Co-authored-by: Peter Hawkins <phawkins@google.com>
 2023-11-20 12:32:50 +01:00
Aryan V S
3ab921166d [Community] [WIP] LCM Interpolation Pipeline (#5767) 
* wip: add interpolate pipeline for lcm

* update documentation

* update documentation
 2023-11-20 12:18:17 +01:00
Kashif Rasul
6b04d61cf6 [Styling] stylify using ruff (#5841) 
* ruff format

* not need to use doc-builder's black styling as the doc is styled in ruff

* make fix-copies

* comment

* use run_ruff
 2023-11-20 11:48:34 +01:00
Sayak Paul
9c7f7fc475 [ControlNet] fix import in single file loading (#5834) 
fix import

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-11-20 15:50:36 +05:30
Aryan V S
4adad57e57 UnboundLocalError in SDXLInpaint.prepare_latents() (#5648) 
* fix: UnboundLocalError with image_latents

* chore: run make style, quality, fix-copies

* revert changes from make fix-copies

* revert changes from make fix-copies

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2023-11-19 22:39:51 -10:00
Younes Belkada
4e54dfe985 [Tests/LoRA/PEFT] Test also on PEFT / transformers / accelerate latest (#5820) 
* add also peft latest on peft CI

* up

* up

* up

* Update .github/workflows/pr_test_peft_backend.yml

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-11-17 19:17:31 +01:00
Sourab Mangrulkar
6f1435332b Speed up the peft lora unload (#5741) 
* Update peft_utils.py

* fix bug

* make the util backwards compatible.

Co-Authored-By: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>

* fix import issue

* refactor the backward compatibilty condition

* rename the conditional variable

* address comments

Co-Authored-By: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* address comment

---------

Co-authored-by: Younes Belkada <49240599+younesbelkada@users.noreply.github.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
 2023-11-17 19:15:44 +01:00
Patrick von Platen
c6f90daea6 [PEFT] Unpin peft (#5850) 2023-11-17 19:15:02 +01:00
Will Berman
2a84e8bb5a fix memory consistency decoder test (#5828) 
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-11-17 09:31:01 -08:00
Lucain
c896b841e4 Set usedforsecurity=False in hashlib methods (FIPS compliance) (#5790) 
* Set usedforsecurity=False in hashlib methods (FIPS compliance)

* update version dependency

* bump hfh version

* bump hfh version
 2023-11-17 14:56:58 +01:00
Sayak Paul
69412d0a15 [Docs] add: japanese sdxl as a reference (#5844) 
add: japanese sdxl as a reference
 2023-11-17 18:14:02 +05:30
Patrick von Platen
913986afa5 Improve setup.py and add dependency check (#5826) 
* put peft in requirements

* correct peft

* correct installs

* make style

* make style
 2023-11-17 12:05:26 +01:00
Steven Liu
ff573ae245 [docs] Fix title (#5831) 
fix section title
 2023-11-17 08:53:11 +05:30
M. Tolga Cangöz
c697f52476 [Docs] Update and make improvements (#5819) 
Update and make improvements
 2023-11-16 13:47:25 -08:00
Suraj Patil
a042909c83 LCM-LoRA docs (#5782) 
* begin doc

* fix examples

* add in toctree

* fix toctree

* improve copy

* improve introductions

* add lcm doc

* fix filename

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* address Sayak's comments

* remove controlnet aux

* open in colab

* move to Specific pipeline examples

* update controlent and adapter examples

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-16 16:19:27 +01:00
Suraj Patil
64cbd8e27a Support LCM in ControlNet and Adapter pipelines. (#5822) 
* support lcm

* fix tests

* fix tests
 2023-11-16 14:59:50 +01:00
Aryan V S
038b42db94 Improve docs and type hints (#5759) 
* improvement: docs and type hints

* improvement: docs and type hints

minor refactor

* improvement: docs and type hints

* update with suggestions from review

Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-11-16 14:00:32 +05:30
M. Tolga Cangöz
ecbe27a07f [Docs] Fix typos and update files at API's Pipelines page 2 (#5748) 
* Fix typos, update, add Copyright info, and trim trailing whitespace

* Update docs/source/en/api/pipelines/text_to_video_zero.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* 1 second is not a long video, but 6 seconds is

* Update text_to_video_zero.md

* Update text_to_video_zero.md

* Update text_to_video_zero.md

* Update wuerstchen.md

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-15 10:54:55 -08:00
M. Tolga Cangöz
3ad4207d1f [Docs] Fix typos, update, and add visualizations at Using Diffusers' Pipelines for Inference Page (#5649) 
* Fix typos, update, add visualizations

* Update sdxl.md

* Update controlnet.md

* Update docs/source/en/using-diffusers/shap-e.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/using-diffusers/shap-e.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update diffedit.md

* Update kandinsky.md

* Update sdxl.md

* Update controlnet.md

* Update docs/source/en/using-diffusers/controlnet.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/using-diffusers/controlnet.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update controlnet.md

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-15 10:30:01 -08:00
MilkClouds
3517fb9430 fix: enabled num_images_per_prompt>1 for lpw_stable_diffusion_xl (community pipeline) (#5807) 
* fix: enabled num_images_per_prompt>1 for lpw_stable_diffusion_xl

* style: fixed isort
 2023-11-15 07:40:29 -10:00
Dhruv Nair
cdadb023a2 Make Video Tests faster (#5787) 
* update test

* update
 2023-11-15 10:56:01 +05:30
M. Tolga Cangöz
51fd3dd206 [Docs] Remove .to('cuda') before .enable_model_cpu_offload() (#5795) 
Remove .to('cuda') before cpu_offload, trim trailing whitespaces
 2023-11-14 17:20:54 -08:00
Pedro Gabriel Gengo Lourenço
98457580c0 Fixed documentation of consistency decoder (#5768) 
* Fixed doc for consistency decoder

* Style fix
 2023-11-14 15:27:26 -08:00
M. Tolga Cangöz
3b37488fa3 Fix typos, improve, update at main-page files and .github files (#5588) 
* Update keywords; remove version cuz it changes constantly?

* Update if necessary

* Fix typos and links

* version_range_max from PyTorch's setup.py; fix typos; 1 checklist is enough?

* Fix a typo

* Fix typos

* There is already a Blank issue link at the bottom of the page; direct to Diffusers' forum

* Add 🌐 Translating a New Language? page

* Update .github/ISSUE_TEMPLATE/translate.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update PHILOSOPHY.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update PHILOSOPHY.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update PHILOSOPHY.md

* Update PHILOSOPHY.md

* Update CONTRIBUTING.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update CONTRIBUTING.md

* Update CONTRIBUTING.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update PHILOSOPHY.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update PHILOSOPHY.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update README.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Add X account link

* Update setup.py

* Update CITATION.cff

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-14 11:46:52 -08:00
Kadir Nar
c7260ce253 🔧 Fix import codes in diffusers library (#5792) 
* 🔧 Fix import codes in diffusers library

* ✨Refactor imports in community examples
 2023-11-14 11:37:59 -08:00
M. Tolga Cangöz
8092017d3f [Docs] Fix typos and update files at API's Pipelines page 1 (#5744) 
* Fix typos, update, add Copyright info, and trim trailing whitespace

* Update alt_diffusion.md

* Remove nonoperational demo

* Update docs/source/en/api/pipelines/consistency_models.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/api/pipelines/latent_consistency_models.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-14 10:36:20 -08:00
Steven Liu
bae14c8bcb [docs] Update training docs (#5512) 
* first draft

* try hfoption syntax

* fix hfoption id

* add text2image

* fix tag

* feedback

* feedbacks

* add textual inversion

* DreamBooth

* lora

* controlnet

* instructpix2pix

* custom diffusion

* t2i

* separate training methods and models

* sdxl

* kandinsky

* wuerstchen

* light edits
 2023-11-14 10:29:56 -08:00
Sayak Paul
ded93f798c [Refactor] refactor loaders.py to make it cleaner and leaner. (#5771) 
* refactor loaders.py to make it cleaner and leaner.

* refactor loaders init

* inits.

* textual inversion to the init.

* inits.

* remove certain modules from the main init.

* AttnProcsLayers

* fix imports

* avoid circular import.

* fix circular import pt 2.

* address PR comments

* imports

* fix: imports.

* remove from main init for avoiding circular deps.

* remove spurious deps.

* fix-copies.

* fix imports.

* more debug

* more debug

* Apply suggestions from code review

* Apply suggestions from code review

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-11-14 12:54:28 +01:00
Sayak Paul
a5720e9e31 [PixArt-Alpha] Fix PixArt-Alpha pipeline when number of images to generate is more than 1 (#5752) 
* does this fix things?

* attention mask use

* attention mask order

* better masking.

* add: tesrt

* remove mask_featur

* test

* debug

* fix: tests

* deprecate mask_feature

* add deprecation test

* add slow test

* add print statements to retrieve the assertion values.

* fix for the 1024 fast tes

* fix tesy

* fix the remaining

* Apply suggestions from code review

* more debug

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-11-14 12:45:35 +01:00
Richard Löwenström
16d500455b Use greater than or equal to in version comparisons for peft (#5785) 2023-11-14 12:17:51 +01:00
Yusuke Suzuki
210a07b13c fix exception around NSFW filter on flax stable diffusion (#5675) 2023-11-14 12:16:52 +01:00
Patrick von Platen
0a0ebc7cb4 [LCM] Better error message (#5788) 2023-11-14 12:08:15 +01:00
Patrick von Platen
81df9c85de Unwrap models everywhere (#5789) 
more debug
 2023-11-14 12:08:03 +01:00
takuoko
bfe94a3993 [Enhacne] Support maybe_raise_or_warn for peft (#5653) 
* Support maybe_raise_or_warn for peft

* fix by comment

* unwrap function
 2023-11-14 11:40:35 +01:00
Lukas Kuhn
c9c5436c94 download_from_original_stable_diffusion_ckpt initializes correct default pipeline for SDXL (#5784) 
* feat: sdxl will be automatically detected as pipeline_class

* fix: formatting

* fix: formatting with black

* fix: import pipeline wrongly sorted
 2023-11-14 11:35:26 +01:00
Sourab Mangrulkar
9c8eca702c add lora delete feature (#5738) 
* add lora delete feature

* added tests and changed condition

* deal with corner cases

* more corner cases

* rename to `delete_adapter_layers` for consistency

---------

Co-authored-by: younesbelkada <younesbelkada@gmail.com>
 2023-11-14 10:51:13 +01:00
co63oc
069123f66e Update checkpoint_merger.py (#5780) 2023-11-14 10:46:11 +01:00
Sayak Paul
ed759f0aee [PixArt-Alpha] Introduce resolution binning (#5739) 
* feat: add resolution binning

Co-authored-by: lawrence-cj <jschen@mail.dlut.edu.cn>

* rename

* debug

* add :test

* remove unused variable

* set resolution_binning to False.

---------

Co-authored-by: lawrence-cj <jschen@mail.dlut.edu.cn>
 2023-11-14 08:34:59 +05:30
Long(Tony) Lian
5b231aa38b Fix the pipeline name in the examples for LMD+ pipeline. Add a colab link to pipeline README. (#5775) 
* Fix the pipeline name in the examples for LMD+ pipeline

* Add LMD+ colab link

* Apply code formatting

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-11-14 07:43:37 +05:30
M. Tolga Cangöz
a359ff7644 [Docs] Fix typos and update files at API's Main Classes, Models, and Schedulers pages (#5720) 
* Fix typos, update, add Copyright info, and trim trailing whitespaces

* Update docs/source/en/api/loaders.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/api/models/autoencoder_tiny.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/api/models/autoencoder_tiny.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-11-13 14:32:59 -08:00
Steven Liu
4b45a1e147 [docs] Use other checkpoints with inpaint (#5590) 
* tip about inpaint checkpoints

* expand section

* feedback
 2023-11-13 12:39:30 -08:00