AI/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-01-29 07:22:12 +03:00
Code Activity
2,783 Commits 742 Branches 94 Tags
3105c710ba16fa2cf54d8deb158099a4146da511
Commit Graph

2783 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Will Berman
3105c710ba [fix] multi t2i adapter set total_downscale_factor (#4621) 
* [fix] multi t2i adapter set total_downscale_factor

* move image checks into check inputs

* remove copied from
 2023-08-24 12:01:23 -07:00
Patrick von Platen
58f5f748f4 [Tests] Fix paint by example (#4761) 
* [Tests] Fix paint by example

* Update src/diffusers/pipelines/paint_by_example/image_encoder.py
 2023-08-24 16:03:10 +02:00
Dhruv Nair
4f05058bb7 Clean up flaky behaviour on Slow CUDA Pytorch Push Tests (#4759) 
use max diff to compare model outputs
 2023-08-24 18:58:02 +05:30
Patrick von Platen
5d4413001b make style 2023-08-24 10:19:47 +00:00
Symbiomatrix
863e741614 Bugfix for SDXL model loading in low ram system. (#4628) 
Update convert_from_ckpt.py

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-24 12:19:16 +02:00
Sanchit Gandhi
24c5e7708b [AudioLDM2] Doc fixes (#4739) 
* [AudioLDM2] Doc fixes

* update docstrings

* fix unet docstring

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-24 07:20:27 +05:30
YiYi Xu
cd21b965d1 add a step_index counter (#4347) 
add self.step_index

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-23 10:49:54 -10:00
Yinzhen Wang
d185b5ed5f change validation scheduler for train_dreambooth.py when training IF (#4333) 
* dreambooth training

* train_dreambooth validation scheduler

* set a particular scheduler via a string

* modify readme after setting a particular scheduler via a string

* modify readme after setting a particular scheduler

* use importlib to set a particular scheduler

* import with correct sort
 2023-08-23 22:18:17 +02:00
Suraj Patil
709a642827 fix dummy import for AudioLDM2 (#4741) 
* fix import

* style
 2023-08-23 22:07:47 +02:00
Sanchit Gandhi
0a0fe69aa6 [AudioLDM Docs] Update docstring (#4744) 2023-08-23 11:04:54 -07:00
realliujiaxu
124e76ddc6 [docs] add variant="fp16" flag (#4678) 2023-08-23 10:00:34 -07:00
Sanchit Gandhi
05b0ec63bc [AudioLDM Docs] Fix docs for output (#4737) 2023-08-23 18:02:11 +02:00
Sayak Paul
4909b1e3ac [Examples] fix checkpointing and casting bugs in train_text_to_image_lora_sdxl.py (#4632) 
* fix: casting issues.

* fix checkpointing.

* tests

* fix: bugs
 2023-08-23 10:58:54 +05:30
Ollin Boer Bohan
052bf3280b Fix AutoencoderTiny encoder scaling convention (#4682) 
* Fix AutoencoderTiny encoder scaling convention

  * Add [-1, 1] -> [0, 1] rescaling to EncoderTiny

  * Move [0, 1] -> [-1, 1] rescaling from AutoencoderTiny.decode to DecoderTiny
    (i.e. immediately after the final conv, as early as possible)

  * Fix missing [0, 255] -> [0, 1] rescaling in AutoencoderTiny.forward

  * Update AutoencoderTinyIntegrationTests to protect against scaling issues.
    The new test constructs a simple image, round-trips it through AutoencoderTiny,
    and confirms the decoded result is approximately equal to the source image.
    This test checks behavior with and without tiling enabled.
    This test will fail if new AutoencoderTiny scaling issues are introduced.

  * Context: Raw TAESD weights expect images in [0, 1], but diffusers'
    convention represents images with zero-centered values in [-1, 1],
    so AutoencoderTiny needs to scale / unscale images at the start of
    encoding and at the end of decoding in order to work with diffusers.

* Re-add existing AutoencoderTiny test, update golden values

* Add comments to AutoencoderTiny.forward
 2023-08-23 08:38:37 +05:30
Patrick von Platen
80871ac597 fix bad error message when transformers is missing (#4714) 2023-08-22 21:25:01 +02:00
Patrick von Platen
6abc66ef28 Fix all docs (#4721) 
* [Docs] Fix all

* fix
 2023-08-22 21:00:21 +02:00
Patrick von Platen
38efac9f61 Revert "Move controlnet load local tests to nightly (#4543)" (#4713) 
This reverts commit 7b07f9812a.
 2023-08-22 19:55:15 +02:00
Patrick von Platen
4f6399bedd rename test file to run, so that examples tests do not fail (#4715) 
* rename test file to run, so that examples tests do not fail

* [Tests] Rename community tests
 2023-08-22 19:54:46 +02:00
Patrick von Platen
6e1af3a777 [Docs] Fix docs controlnet missing /Tip (#4717) 2023-08-22 18:40:26 +02:00
zideliu
f22aad6e3a Add reference_attn & reference_adain support for sdxl (#4502) 
* ADD SDXL reference & reference adain

* Update README.md

* Update README.md

* format stable_diffusion_xl_reference.py

* format file

* Format file

* format file

* fix format

* fix format with ruff

* fix format

* Update examples/community/README.md

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* Update examples/community/README.md

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* Update README.md

* Update README.md & fix typo

* Update README.md

* fix format

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-08-22 20:22:01 +05:30
realliujiaxu
ecded50ad5 add convert diffuser pipeline of XL to original stable diffusion (#4596) 
convert diffuser pipeline of XL to original stable diffusion

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-08-22 19:11:06 +05:30
Alex McKinney
e34d9aa681 Replaces DIFFUSERS_TEST_DEVICE backend list with trying device (#4673) 
This is a better method than comparing against a list of supported backends as it allows for supporting any number of backends provided they are installed on the user's system.
This should have no effect on the behaviour of tests in Huggingface's CI workers.
See transformers#25506 where this approach has already been added.
 2023-08-22 11:48:12 +05:30
Sayak Paul
8d30d25794 [LoRA] default to None when fc alphas are not available. (#4706) 
default to None when fc alphas are not available.
 2023-08-22 08:47:08 +05:30
Sayak Paul
1e0395e791 [LoRA] ensure different LoRA ranks for text encoders can be properly handled (#4669) 
* debugging starts

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging ends, but does it?

* more robustness.
 2023-08-22 08:21:13 +05:30
Sayak Paul
9141c1f9d5 [Core] enable lora for sdxl controlnets too and add slow tests. (#4666) 
* enable lora for sdxl controlnets too.

* add: tests

* fix: assertion values.
 2023-08-22 07:13:23 +05:30
dg845
f75b8aa9dd [docs] Add note in UniDiffusers Doc about PyTorch 1.X numerical stability issue (#4703) 
* Add note regarding UniDiffuser pipeline numerical stability issues on PyTorch 1.X

* Use the doc-builder warning tag.
 2023-08-22 07:12:06 +05:30
Sanchit Gandhi
7a24977ce3 Add AudioLDM 2 (#4549) 
* from audioldm

* unet down + mid

* vae, clap, flan-t5

* start sequence audio mae

* iterate on audioldm encoder

* finish encoder

* finish weight conversion

* text pre-processing

* gpt2 pre-processing

* fix projection model

* working

* unet equivalence

* finish in base

* add unet cond

* finish unet

* finish custom unet

* start clean-up

* revert base unet changes

* refactor pre-processing

* tests: from audioldm

* fix some tests

* more fixes

* iterate on tests

* make fix copies

* harden fast tests

* slow integration tests

* finish tests

* update checkpoint

* update copyright

* docs

* remove outdated method

* add docstring

* make style

* remove decode latents

* enable cpu offload

* (text_encoder_1, tokenizer_1) -> (text_encoder, tokenizer)

* more clean up

* more refactor

* build pr docs

* Update docs/source/en/api/pipelines/audioldm2.md

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

* small clean

* tidy conversion

* update for large checkpoint

* generate -> generate_language_model

* full clap model

* shrink clap-audio in tests

* fix large integration test

* fix fast tests

* use generation config

* make style

* update docs

* finish docs

* finish doc

* update tests

* fix last test

* syntax

* finalise tests

* refactor projection model in prep for TTS

* fix fast tests

* style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-08-21 12:34:21 +01:00
zuojianghua
74d902eb59 add config_file to from_single_file (#4614) 
* Update loaders.py

add config_file to from_single_file, 
when the download_from_original_stable_diffusion_ckpt use

* Update loaders.py

add config_file to from_single_file,
when the download_from_original_stable_diffusion_ckpt use

* change config_file to original_config_file

* make style && make quality

---------

Co-authored-by: jianghua.zuo <jianghua.zuo@weimob.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-08-18 19:33:12 +05:30
Andrew Zhu
d7c4ae619d Add SDXL long weighted prompt pipeline (replace pr:4629) (#4661) 
* Add SDXL long weighted prompt pipeline

* Add SDXL long weighted prompt pipeline usage sample in the readme document

* Add SDXL long weighted prompt pipeline usage sample in the readme document, add result image
 2023-08-18 11:30:10 +05:30
Isotr0py
67ea2b7afa Support tiled encode/decode for AutoencoderTiny (#4627) 
* Impl tae slicing and tiling

* add tae tiling test

* add parameterized test

* formatted code

* fix failed test

* style docs
 2023-08-18 09:12:55 +05:30
Sayak Paul
a10107f92b fix: lora sdxl tests (#4652) 2023-08-17 15:59:50 +05:30
Sayak Paul
d0c30cfd37 make post-release (#4650) 2023-08-17 14:16:25 +05:30
Jacqui Wei
7c3e7fedcd Fix use_onnx parameter usage in from_pretrained func and update test_download_no_onnx_by_default test (#4508) 
* add missing use_onnx in from_pretrained func

* fix test_download_no_onnx_by_default test func

* address comments

* split test cases
 2023-08-17 11:49:32 +05:30
Patrick von Platen
029fb41695 [Safetensors] Make safetensors the default way of saving weights (#4235) 
* make safetensors default

* set default save method as safetensors

* update tests

* update to support saving safetensors

* update test to account for safetensors default

* update example tests to use safetensors

* update example to support safetensors

* update unet tests for safetensors

* fix failing loader tests

* fix qc issues

* fix pipeline tests

* fix example test

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2023-08-17 10:54:28 +05:30
Batuhan Taskaya
852dc76d6d Support higher dimension LoRAs (#4625) 
* Support higher dimension LoRAs

* add: tests

* fix: assertion values.

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-08-17 10:07:07 +05:30
Scott Lessans
064f150813 Fix UnboundLocalError during LoRA loading (#4523) 
* fixed

* add: tests

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-08-17 09:33:35 +05:30
Sayak Paul
5333f4c0ec make things clear in the controlnet sdxl doc. (#4644) 2023-08-17 09:04:28 +05:30
Dhruv Nair
3d08d8dc4e fix loading custom text encoder when using from_single_file (#4571) 
fix loading custom text encoder when using from_single_file
 2023-08-17 08:41:09 +05:30
Steven Liu
bdc4c3265f [docs] MultiControlNet (#4635) 
multicontrolnet docs
 2023-08-17 08:14:20 +05:30
Steven Liu
4ff7264d9b [docs] PushToHubMixin (#4622) 
* push to hub docs

* fix typo

* feedback

* make style
 2023-08-16 13:20:59 -06:00
Sayak Paul
5049599143 [Core] feat: MultiControlNet support for SDXL ControlNet pipeline (#4597) 
* core: add multicontrolnet support to sdxl controlnet

* modify checks.

* fix: original_size determination

* add: tests for multi controlnet sdxl.

* remove unnecessary prints.
 2023-08-16 20:30:39 +05:30
Suraj Patil
7b93c2a882 [research_projects] SDXL controlnet script (#4633) 
add controlent script,
 2023-08-16 18:27:08 +05:30
Dirk Morris
a7de96505b Fix unipc use_karras_sigmas exception - fixes huggingface/diffusers#4580 (#4581) 
* Fix unipc karras sigmas exception - fixes huggingface/diffusers#4580

* Add unipc scheduler tests for karras sigmas
 2023-08-16 10:01:53 +05:30
Sayak Paul
351aab60e9 Update text2image.md to fix the links (#4626) 2023-08-16 09:53:10 +05:30
nikhil-masterful
da5ab51d54 Add GLIGEN implementation (#4441) 
* Add GLIGEN implementation

* GLIGEN: Fix code quality check failures

* GLIGEN: Fix Import block un-sorted or un-formatted failures

* GLIGEN: Fix check_repository_consistency failures

* GLIGEN: Add 'PositionNet' to versatile_diffusion/modeling_text_unet.py

* GLIGEN: check_repository_consistency: fix 'copy does not match' error

* GLIGEN: Fix review comments (1)

* GLIGEN: Fix E721 Do not compare types, use `isinstance()` failures

* GLIGEN : Ensure _encode_prompt() copy matches to StableDiffusionPipeline

* GLIGEN: Fix ruff E721 failure in unidiffuser/test_unidiffuser.py

* GLIGEN: doc_builder: restyle pipeline_stable_diffusion_gligen.py

* GIGLEN: reset files unrelated to gligen

* GLIGEN: Fix documentation comments (1)

* GLIGEN: Fix review comments (2)

* GLIGEN: Added FastTest

* GLIGEN: Fix review comments (3)
 2023-08-16 09:34:17 +05:30
Sayak Paul
5175d3d7a5 add: train to text image with sdxl script. (#4505) 
* add: train to text image with sdxl script.

Co-authored-by: CaptnSeraph <s3raph1m@gmail.com>

* fix: partial func.

* fix: default value of output_dir.

* make style

* set num inference steps to 25.

* remove mentions of LoRA.

* up min version

* add: ema cli arg

* run device placement while running step.

* precompute vae encodings too.

* fix

* debug

* should work now.

* debug

* debug

* goes alright?

* style

* debugging

* debugging

* debugging

* debugging

* fix

* reinit scheduler if prediction_type was passed.

* akways cast vae in float32

* better handling of snr.

Co-authored-by: bghira <bghira@users.github.com>

* the vae should be also passed

* add: docs.

* add: sdlx t2i tests

* save the pipeline

* autocast.

* fix: save_model_card

* fix: save_model_card.

---------

Co-authored-by: CaptnSeraph <s3raph1m@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: bghira <bghira@users.github.com>
 2023-08-16 09:02:49 +05:30
Sayak Paul
a7508a76f0 add: pushtohubmixin to pipelines and schedulers docs overview. (#4607) 
* add: pushtohubmixin to pipelines and schedulers docs overview.

* Apply suggestions from code review

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

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2023-08-15 22:23:17 +05:30
Sayak Paul
aaef41b5fe [Docs] fix links in the controlling generation doc. (#4612) 
* fix links in the controlling generation doc.

* more fixes.
 2023-08-15 20:27:13 +05:30
Wang Qiang
078df46bc9 An invalid clerical error in sdxl finetune (#4608) 2023-08-15 10:41:51 +05:30
Sayak Paul
15782fd506 [Pipeline utils] feat: implement push_to_hub for standalone models, schedulers as well as pipelines (#4128) 
* feat: implement push_to_hub for standalone models.

* address PR feedback.

* Apply suggestions from code review

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* remove max_shard_size.

* add: support for scheduler push_to_hub

* enable push_to_hub support for flax schedulers.

* enable push_to_hub for pipelines.

* Apply suggestions from code review

Co-authored-by: Lucain <lucainp@gmail.com>

* reflect pr feedback.

* address another round of deedback.

* better handling of kwargs.

* add: tests

* Apply suggestions from code review

Co-authored-by: Lucain <lucainp@gmail.com>

* setting hub staging to False for now.

* incorporate staging test as a separate job.

Co-authored-by: ydshieh <2521628+ydshieh@users.noreply.github.com>

* fix: tokenizer loading.

* fix: json dumping.

* move is_staging_test to a better location.

* better treatment to tokens.

* define repo_id to better handle concurrency

* style

* explicitly set token

* Empty-Commit

* move SUER, TOKEN to test

* collate org_repo_id

* delete repo

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: ydshieh <2521628+ydshieh@users.noreply.github.com>
 2023-08-15 07:39:22 +05:30