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
2,795 Commits 740 Branches 94 Tags
dc8da1d44922c2e2a6731c70a4fa7789cd983bb2
Commit Graph

2795 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Mayank Khanduja
dc8da1d449 Fixed broken link of CLIP doc in evaluation doc (#4760) 2023-08-25 20:04:50 +02:00
Zijian He
3dd540171d fix bug of progress bar in clip guided images mixing (#4729) 2023-08-25 18:54:03 +02:00
YiYi Xu
b3b2d30cd8 fix a bug in from_pretrained when load optional components (#4745) 
* fix
---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-25 06:25:48 -10:00
Dhruv Nair
3bba44d74e [WIP ] Proposal to address precision issues in CI (#4775) 
* proposal for flaky tests

* clean up
 2023-08-25 19:12:09 +05:30
Sanchit Gandhi
b1290d3fb8 Convert MusicLDM (#4579) 
* from audioldm

* fix vae

* move to new pipeline

* copied from audioldm

* remove redundant control flow

* iterate

* fix docstring

* finish pipeline

* tests: from audioldm2

* iterate

* finish fast tests

* finish slow integration tests

* add docs

* remove dtype test

* update toctree

* "copied from" in conversion (where possible)

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

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

* fix docstring

* make nightly

* style

* fix dtype test

---------

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
 2023-08-25 13:31:00 +01:00
Sanchit Gandhi
29a11c2a94 [AudioLDM 2] Pipeline fixes (#4738) 
* fix docs

* fix unet docs

* use image output for latents

* fix hub checkpoints

* fix pipeline example

* update example

* return_dict = False

* revert image pipeline output

* revert doc changes

* remove dtype test

* make style

* remove docstring updates

* remove unet docstring update

* Empty commit to re-trigger CI

* fix cpu offload

* fix dtype test

* add offload test
 2023-08-25 11:38:10 +01:00
Patrick von Platen
cdacd8f1dd Torch device (#4755) 2023-08-25 11:13:32 +02:00
Sayak Paul
470d51c8ed improve setup.py (#4748) 2023-08-25 13:44:20 +05:30
Andrew Zhu
d6141205cd fix sdxl_lwp empty neg_prompt error issue (#4743) 
* fix sdxl_lwp empty neg_prompt error issue

* fix sdxl_lwp empty neg_prompt error issue, update code format

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2023-08-25 09:55:56 +05:30
Sayak Paul
4447547eda [Examples] fix sdxl dreambooth lora checkpointing. (#4749) 
* fix sdxl dreambooth lora checkpointing.

* style
 2023-08-25 09:50:02 +05:30
Sayak Paul
5222294748 [LoRA] relax lora loading logic (#4610) 
* relax lora loading logic.

* cater to the other cases too.

* fix: variable name

* bring the chaos down.

* check

* deal with checkpointed files.

* Apply suggestions from code review

Co-authored-by: apolinário <joaopaulo.passos@gmail.com>

* style

---------

Co-authored-by: apolinário <joaopaulo.passos@gmail.com>
 2023-08-25 09:35:51 +05:30
Mario Namtao Shianti Larcher
c25c46137d [Examples] Add madebyollin VAE to SDXL LoRA example, along with an explanation (#4762) 
Add madebyollin VAE to LoRA example, along with an explenation
 2023-08-25 09:34:32 +05:30
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