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
4,800 Commits 740 Branches 94 Tags
3cb7b8628cbade13fe0c76aa9ff203d0844da454
Commit Graph

4800 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Juan Acevedo
3cb7b8628c Update ptxla training (#9864) 
* update ptxla example

---------

Co-authored-by: Juan Acevedo <jfacevedo@google.com>
Co-authored-by: Pei Zhang <zpcore@gmail.com>
Co-authored-by: Pei Zhang <piz@google.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Pei Zhang <pei@Peis-MacBook-Pro.local>
Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-06 10:50:13 -10:00
Sayak Paul
fa3a9100be [LoRA] depcrecate save_attn_procs(). (#10126) 
depcrecate save_attn_procs().
 2024-12-06 10:38:57 -10:00
zhangp365
188bca3084 fixed a dtype bfloat16 bug in torch_utils.py (#10125) 
* fixed a dtype bfloat16 bug in torch_utils.py

when generating 1024*1024 image with bfloat16 dtype, there is an exception:
  File "/opt/conda/lib/python3.10/site-packages/diffusers/utils/torch_utils.py", line 107, in fourier_filter
    x_freq = fftn(x, dim=(-2, -1))
RuntimeError: Unsupported dtype BFloat16

* remove whitespace in torch_utils.py

* Update src/diffusers/utils/torch_utils.py

* Update torch_utils.py

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-06 10:36:39 -10:00
Junsong Chen
cd892041e2 [DC-AE] Add the official Deep Compression Autoencoder code(32x,64x,128x compression ratio); (#9708) 
* first add a script for DC-AE;

* DC-AE init

* replace triton with custom implementation

* 1. rename file and remove un-used codes;

* no longer rely on omegaconf and dataclass

* replace custom activation with diffuers activation

* remove dc_ae attention in attention_processor.py

* iinherit from ModelMixin

* inherit from ConfigMixin

* dc-ae reduce to one file

* update downsample and upsample

* clean code

* support DecoderOutput

* remove get_same_padding and val2tuple

* remove autocast and some assert

* update ResBlock

* remove contents within super().__init__

* Update src/diffusers/models/autoencoders/dc_ae.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* remove opsequential

* update other blocks to support the removal of build_norm

* remove build encoder/decoder project in/out

* remove inheritance of RMSNorm2d from LayerNorm

* remove reset_parameters for RMSNorm2d

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* remove device and dtype in RMSNorm2d __init__

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/dc_ae.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/dc_ae.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/autoencoders/dc_ae.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* remove op_list & build_block

* remove build_stage_main

* change file name to autoencoder_dc

* move LiteMLA to attention.py

* align with other vae decode output;

* add DC-AE into init files;

* update

* make quality && make style;

* quick push before dgx disappears again

* update

* make style

* update

* update

* fix

* refactor

* refactor

* refactor

* update

* possibly change to nn.Linear

* refactor

* make fix-copies

* replace vae with ae

* replace get_block_from_block_type to get_block

* replace downsample_block_type from Conv to conv for consistency

* add scaling factors

* incorporate changes for all checkpoints

* make style

* move mla to attention processor file; split qkv conv to linears

* refactor

* add tests

* from original file loader

* add docs

* add standard autoencoder methods

* combine attention processor

* fix tests

* update

* minor fix

* minor fix

* minor fix & in/out shortcut rename

* minor fix

* make style

* fix paper link

* update docs

* update single file loading

* make style

* remove single file loading support; todo for DN6

* Apply suggestions from code review

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

* add abstract

---------

Co-authored-by: Junyu Chen <chenjydl2003@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: chenjy2003 <70215701+chenjy2003@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-07 01:01:51 +05:30
suzukimain
6394d905da [community] Load Models from Sources like Civitai into Existing Pipelines (#9986) 
* Added example of model search.

* Combine processing into one file

* Add parameters for base model

* Bug Fixes

* bug fix

* Create README.md

* Update search_for_civitai_and_HF.py

* Create requirements.txt

* bug fix

* Update README.md

* bug fix

* Correction of typos

* Update examples/model_search/README.md

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

* Update examples/model_search/README.md

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

* Update examples/model_search/README.md

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

* Update examples/model_search/README.md

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

* Update examples/model_search/README.md

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

* Update examples/model_search/README.md

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

* apply the changes

* Replace search_for_civitai_and_HF.py with pipeline_easy.py

* Update examples/model_search/README.md

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

* Update examples/model_search/README.md

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

* Update examples/model_search/README.md

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

* Update README.md

* Organize the table of parameters

* Update README.md

* Update README.md

* Update README.md

* make style

* Fixing the style of pipeline

* Fix pipeline style

* fix

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-06 07:48:45 -08:00
Aryan
18f9b99088 Remove duplicate checks for len(generator) != batch_size when generator is a list (#10134) 
remove duplicate checks
 2024-12-06 11:29:10 +00:00
Aritra Roy Gosthipaty
bf64b32652 [Guide] Quantize your Diffusion Models with bnb (#10012) 
* chore: initial draft

* Apply suggestions from code review

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* chore: link in place

* chore: review suggestions

* Apply suggestions from code review

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

* chore: review suggestions

* Update docs/source/en/quantization/bitsandbytes.md

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

* review suggestions

* chore: review suggestions

* Apply suggestions from code review

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

* adding same changes to 4 bit section

* review suggestions

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-05 13:54:03 -08:00
SahilCarterr
3335e2262d [FIX] Bug in FluxPosEmbed (#10115) 
* Fix get_1d_rotary_pos_embed in embedding.py

* Update embeddings.py

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-05 13:12:48 +00:00
Sayak Paul
65ab1052b8 [Tests] xfail incompatible SD configs. (#10127) 
* xfail incompatible SD configs.

* fix
 2024-12-05 15:11:52 +05:30
Sayak Paul
40fc389c44 [Tests] fix condition argument in xfail. (#10099) 
* fix condition argument in xfail.

* revert init changes.
 2024-12-05 10:13:45 +05:30
Aryan
98d0cd5778 Use torch.device instead of current device index for BnB quantizer (#10069) 
* update

* apply review suggestion

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-05 08:05:24 +05:30
Steven Liu
0d11ab26c4 [docs] load_lora_adapter (#10119) 
* load_lora_adapter

* save

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-05 08:00:03 +05:30
YiYi Xu
243d9a4986 pass attn mask arg for flux (#10122) 2024-12-04 14:22:36 -10:00
linjiapro
96220390a2 Fix a bug for SD35 control net training and improve control net block index (#10065) 
* wip

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-04 14:20:05 -10:00
zhangp365
73dac0c49e Fix a bug in the state dict judgment in ip_adapter.py. (#10095) 
* fix a judging state dict bug in ip_adapter.py

* make

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-04 14:03:43 -10:00
Linoy Tsaban
04bba38725 [Flux Redux] add prompt & multiple image input (#10056) 
* add multiple prompts to flux redux

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-04 08:48:32 -10:00
hlky
a2d424eb2e Add sigmas to pipelines using FlowMatch (#10116) 2024-12-04 08:42:47 -10:00
Parag Ekbote
25ddc7945b Fix Broken Links in ReadMe (#10117) 
Update broken links in ReadME.
 2024-12-04 09:04:31 -08:00
Sayak Paul
e8da75dff5 [bitsandbytes] allow directly CUDA placements of pipelines loaded with bnb components (#9840) 
* allow device placement when using bnb quantization.

* warning.

* tests

* fixes

* docs.

* require accelerate version.

* remove print.

* revert to()

* tests

* fixes

* fix: missing AutoencoderKL lora adapter (#9807)

* fix: missing AutoencoderKL lora adapter

* fix

---------

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

* fixes

* fix condition test

* updates

* updates

* remove is_offloaded.

* fixes

* better

* empty

---------

Co-authored-by: Emmanuel Benazera <emmanuel.benazera@jolibrain.com>
 2024-12-04 22:27:43 +05:30
hlky
8a450c3da0 Fix pipeline_stable_audio formating (#10114) 2024-12-04 17:47:42 +05:30
fancy45daddy
9ff72433fa add torch_xla support in pipeline_stable_audio.py (#10109) 
Update pipeline_stable_audio.py
 2024-12-04 11:24:22 +00:00
Sayak Paul
c1926cef6b [tests] refactor vae tests (#9808) 
* add: autoencoderkl tests

* autoencodertiny.

* fix

* asymmetric autoencoder.

* more

* integration tests for stable audio decoder.

* consistency decoder vae tests

* remove grad check from consistency decoder.

* cog

* bye test_models_vae.py

* fix

* fix

* remove allegro

* fixes

* fixes

* fixes

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-04 15:58:36 +05:30
Ivan Skorokhodov
8421c1461b Use parameters + buffers when deciding upscale_dtype (#9882) 
Sometimes, the decoder might lack parameters and only buffers (e.g., this happens when we manually need to convert all the parameters to buffers — e.g. to avoid packing fp16 and fp32 parameters with FSDP)
 2024-12-03 21:20:11 -10:00
hlky
cfdeebd4a8 Test skip_guidance_layers in SD3 pipeline (#10102) 
* Test `skip_guidance_layers` in pipelines

* Move to test_pipeline_stable_diffusion_3
 2024-12-03 14:28:31 -10:00
hlky
6a51427b6a Fix multi-prompt inference (#10103) 
* Fix multi-prompt inference

Fix generation of multiple images with multiple prompts, e.g len(prompts)>1, num_images_per_prompt>1

* make

* fix copies

---------

Co-authored-by: Nikita Balabin <nikita@mxl.ru>
 2024-12-03 13:58:31 -10:00
Anand Kumar
5effcd3e64 [Bug fix] "previous_timestep()" in DDPM scheduling compatible with "trailing" and "linspace" options (#9384) 
* Update scheduling_ddpm.py

* fix copies

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-03 13:57:52 -10:00
lsb
619b9658e2 Avoid compiling a progress bar. (#10098) 
* Avoid creating a progress bar when it is disabled.

This is useful when exporting a pipeline, and allows a compiler to avoid trying to compile away tqdm.

* Prevent the PyTorch compiler from compiling progress bars.

* Update pipeline_utils.py
 2024-12-03 11:54:32 -10:00
aihao
b58f67f2d5 update (#7067) 
* add data_dir parameter to load_dataset

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-03 11:26:47 -10:00
StAlKeR7779
8ac6de963c DPM++ third order fixes (#9104) 
* Fix wrong output on 3n-1 steps count

* Add sde handling to 3 order

* make

* copies

---------

Co-authored-by: hlky <hlky@hlky.ac>
 2024-12-03 11:21:37 -10:00
Parag Ekbote
2be66e6aa0 Fix Broken Link in Optimization Docs (#10105) 
Update broken link.
 2024-12-03 10:23:35 -08:00
Parag Ekbote
cf258948b2 Notebooks for Community Scripts-4 (#10094) 
* Add Diffuser Notebooks for Community Scripts.

* Add missing link.

* Styling Improvement.
 2024-12-03 10:23:00 -08:00
Benjamin Paine
63b631f383 Add StableDiffusion3PAGImg2Img Pipeline + Fix SD3 Unconditional PAG (#9932) 
* fix progress bar updates in SD 1.5 PAG Img2Img pipeline



---------

Co-authored-by: Vinh H. Pham <phamvinh257@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-02 21:39:47 -10:00
Pedro Cuenca
acf79b3487 Don't stale close-to-merge (#10096) 
Re: https://github.com/huggingface/diffusers/discussions/10046#discussioncomment-11443466
 2024-12-03 13:00:01 +05:30
DTG
fc72e0f261 Fix some documentation in ./src/diffusers/models/embeddings.py for demo (#9579) 
* Fix some documentation in ./src/diffusers/models/embeddings.py as demonstration.


---------

Co-authored-by: DaAccursed05 <68813178+DaAccursed05@users.noreply.github.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2024-12-02 17:42:52 -10:00
Lucain
0763a7edf4 Let server decide default repo visibility (#10047) 2024-12-02 17:15:46 -10:00
Emmanuel Benazera
963ffca434 fix: missing AutoencoderKL lora adapter (#9807) 
* fix: missing AutoencoderKL lora adapter

* fix

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-02 17:10:20 -10:00
hlky
30f2e9bd20 Convert sigmas to np.array in FlowMatch set_timesteps (#10088) 2024-12-02 14:18:40 -10:00
Pedro Cuenca
2312b27f79 Interpolate fix on cuda for large output tensors (#10067) 
* Workaround for upscale with large output tensors.

Fixes #10040.

* Fix scale when output_size is given

* Style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-02 13:33:56 -10:00
Dhruv Nair
6db33337a4 [Single File] Pass token when fetching interpreted config (#10082) 
update
 2024-12-02 11:55:36 -10:00
hlky
beb856685d Fix num_images_per_prompt>1 with Skip Guidance Layers in StableDiffusion3Pipeline (#10086) 2024-12-02 21:43:03 +00:00
Dhruv Nair
a9d3f6c359 [Single File] Fix SD3.5 single file loading (#10077) 
update
 2024-12-02 11:16:16 -10:00
YiYi Xu
cd344393e2 fix offloading for sd3.5 controlnets (#10072) 
* add
 2024-12-02 10:11:25 -10:00
ChG
c44fba8899 fix link in the docs (#10058) 
* fix link in the docs

* fix same issue for ko
 2024-12-02 11:45:12 -08:00
Parag Ekbote
922c5f5c3c Fixed Nits in Evaluation Docs (#10063) 
Minor fixes and script improvement in evaluation
docs.
 2024-12-02 10:50:00 -08:00
hlky
8d386f7990 Add sigmas to Flux pipelines (#10081) 2024-12-02 08:16:47 -10:00
Sayak Paul
827b6c25f9 [CI] Add quantization (#9832) 
* add quantization to nightly CI.

* prep.

* fix lib name.

* remove deps that are not needed.

* fix slice.
 2024-12-02 14:53:43 +05:30
SahilCarterr
784b351f32 [Fix] Syntax error (#10068) 
fix syntax error
 2024-12-02 11:28:00 +05:30
Sayak Paul
c96bfa5c80 [Mochi-1] ensuring to compute the fourier features in FP32 in Mochi encoder (#10031) 
compute fourier features in FP32.
 2024-11-29 14:15:00 +05:30
Fanli Lin
6b288ec44d make pipelines tests device-agnostic (part2) (#9400) 
* enable on xpu

* add 1 more

* add one more

* enable more

* add 1 more

* add more

* enable 1

* enable more cases

* enable

* enable

* update comment

* one more

* enable 1

* add more cases

* enable xpu

* add one more caswe

* add more cases

* add 1

* add more

* add more cases

* add case

* enable

* add more

* add more

* add more

* enbale more

* add more

* update code

* update test marker

* add skip back

* update comment

* remove single files

* remove

* style

* add

* revert

* reformat

* enable

* enable esingle g

* add 2 more

* update decorator

* update

* update

* update

* Update tests/pipelines/deepfloyd_if/test_if.py

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

* Update src/diffusers/utils/testing_utils.py

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

* Update tests/pipelines/animatediff/test_animatediff_controlnet.py

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

* Update tests/pipelines/animatediff/test_animatediff.py

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

* Update tests/pipelines/animatediff/test_animatediff_controlnet.py

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

* update float16

* no unitest.skipt

* update

* apply style check

* adapt style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-11-29 11:33:41 +05:30
Álvaro Somoza
fdec8bd675 Change image_gen_aux repository URL (#10048) 
change image_gen_aux repo url
 2024-11-28 12:57:55 -05:00