obscura/diffusers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
4,913 Commits 711 Branches 93 Tags
4c5082ca685d1dd0a24907890da170e258e5cd01
Commit Graph

1081 Commits

Author SHA1 Message Date
Linoy Tsaban 6e9c6a298b [Flux] Dreambooth LoRA training scripts (#9086) 
* initial commit - dreambooth for flux

* update transformer to be FluxTransformer2DModel

* update training loop and validation inference

* fix sd3->flux docs

* add guidance handling, not sure if it makes sense(?)

* inital dreambooth lora commit

* fix text_ids in compute_text_embeddings

* fix imports of static methods

* fix pipeline loading in readme, remove auto1111 docs for now

* fix pipeline loading in readme, remove auto1111 docs for now, remove some irrelevant text_encoder_3 refs

* Update examples/dreambooth/train_dreambooth_flux.py

Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>

* fix te2 loading and remove te2 refs from text encoder training

* fix tokenizer_2 initialization

* remove text_encoder training refs from lora script (for now)

* try with vae in bfloat16, fix model hook save

* fix tokenization

* fix static imports

* fix CLIP import

* remove text_encoder training refs (for now) from lora script

* fix minor bug in encode_prompt, add guidance def in lora script, ...

* fix unpack_latents args

* fix license in readme

* add "none" to weighting_scheme options for uniform sampling

* style

* adapt model saving - remove text encoder refs

* adapt model loading - remove text encoder refs

* initial commit for readme

* Update examples/dreambooth/train_dreambooth_lora_flux.py

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

* Update examples/dreambooth/train_dreambooth_lora_flux.py

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

* fix vae casting

* remove precondition_outputs

* readme

* readme

* style

* readme

* readme

* update weighting scheme default & docs

* style

* add text_encoder training to lora script, change vae_scale_factor value in both

* style

* text encoder training fixes

* style

* update readme

* minor fixes

* fix te params

* fix te params

---------

Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:15 +05:30
Monjoy Narayan Choudhury a46c3d7f90 Add Differential Diffusion to HunyuanDiT. (#9040) 
* Add Differential Pipeline.

* Fix Styling Issue using ruff -fix

* Add details to Contributing.md

* Revert "Fix Styling Issue using ruff -fix"

This reverts commit d347de162d.

* Revert "Revert "Fix Styling Issue using ruff -fix""

This reverts commit ce7c3ff216.

* Revert README changes

* Restore README.md

* Update README.md

* Resolved Comments:

* Fix Readme based on review

* Fix formatting after make style

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2024-12-23 13:02:15 +05:30
sayantan sadhu 23e204790d fix for lr scheduler in distributed training (#9103) 
* fix for lr scheduler in distributed training

* Fixed the recalculation of the total training step section

* Fixed lint error

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:15 +05:30
Sayak Paul f35bdb6a03 fix train_dreambooth_lora_sd3.py loading hook (#9107) 2024-12-23 13:02:15 +05:30
Tolga Cangöz 51f45da25f Update CLIPFeatureExtractor to CLIPImageProcessor and DPTFeatureExtractor to DPTImageProcessor (#9002) 
* fix: update `CLIPFeatureExtractor` to `CLIPImageProcessor` in codebase

* `make style && make quality`

* Update `DPTFeatureExtractor` to `DPTImageProcessor` in codebase

* `make style`

---------

Co-authored-by: Aryan <aryan@huggingface.co>
 2024-12-23 13:02:15 +05:30
omahs 49544cc1fb Fix typos (#9077) 
* fix typo
 2024-12-23 13:02:15 +05:30
asfiyab-nvidia fce5debd8c Update TensorRT txt2img and inpaint community pipelines (#9037) 
* Update TensorRT txt2img and inpaint community pipelines

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

* update tensorrt install instructions

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

---------

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:15 +05:30
Tolga Cangöz c6ac793955 Errata: Fix typos & \s+$ (#9008) 
* Fix typos

* chore: Fix typos

* chore: Update README.md for promptdiffusion example

* Trim trailing white spaces

* Fix a typo

* update number

* chore: update number

* Trim trailing white space

* Update README.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>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Anatoly Belikov c7452308f5 handle lora scale and clip skip in lpw sd and sdxl community pipelines (#8988) 
* handle lora scale and clip skip in lpw sd and sdxl

* use StableDiffusionLoraLoaderMixin

* use StableDiffusionXLLoraLoaderMixin

* style

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul 6d11129c5a [Chore] add LoraLoaderMixin to the inits (#8981) 
* introduce  to promote reusability.

* up

* add more tests

* up

* remove comments.

* fix fuse_nan test

* clarify the scope of fuse_lora and unfuse_lora

* remove space

* rewrite fuse_lora a bit.

* feedback

* copy over load_lora_into_text_encoder.

* address dhruv's feedback.

* fix-copies

* fix issubclass.

* num_fused_loras

* fix

* fix

* remove mapping

* up

* fix

* style

* fix-copies

* change to SD3TransformerLoRALoadersMixin

* Apply suggestions from code review

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

* up

* handle wuerstchen

* up

* move lora to lora_pipeline.py

* up

* fix-copies

* fix documentation.

* comment set_adapters().

* fix-copies

* fix set_adapters() at the model level.

* fix?

* fix

* loraloadermixin.

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:14 +05:30
YiYi Xu a754d9071e Revert "[LoRA] introduce LoraBaseMixin to promote reusability." (#8976) 
Revert "[LoRA] introduce LoraBaseMixin to promote reusability. (#8774)"

This reverts commit 527430d0a4.
 2024-12-23 13:02:14 +05:30
asfiyab-nvidia d1e1676b9d Update TensorRT img2img community pipeline (#8899) 
* Update TensorRT img2img pipeline

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

* Update TensorRT version installed

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

* make style and quality

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

* Update examples/community/stable_diffusion_tensorrt_img2img.py

Co-authored-by: Tolga Cangöz <46008593+tolgacangoz@users.noreply.github.com>

* Update examples/community/README.md

Co-authored-by: Tolga Cangöz <46008593+tolgacangoz@users.noreply.github.com>

* Apply style and quality using ruff 0.1.5

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

---------

Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
Co-authored-by: Tolga Cangöz <46008593+tolgacangoz@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul 82b37a4cc3 [LoRA] introduce LoraBaseMixin to promote reusability. (#8774) 
* introduce  to promote reusability.

* up

* add more tests

* up

* remove comments.

* fix fuse_nan test

* clarify the scope of fuse_lora and unfuse_lora

* remove space

* rewrite fuse_lora a bit.

* feedback

* copy over load_lora_into_text_encoder.

* address dhruv's feedback.

* fix-copies

* fix issubclass.

* num_fused_loras

* fix

* fix

* remove mapping

* up

* fix

* style

* fix-copies

* change to SD3TransformerLoRALoadersMixin

* Apply suggestions from code review

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

* up

* handle wuerstchen

* up

* move lora to lora_pipeline.py

* up

* fix-copies

* fix documentation.

* comment set_adapters().

* fix-copies

* fix set_adapters() at the model level.

* fix?

* fix

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2024-12-23 13:02:14 +05:30
Dhruv Nair df4e3f45c1 Fix name when saving text inversion embeddings in dreambooth advanced scripts (#8927) 
update
 2024-12-23 13:02:14 +05:30
akbaig 2d738e2c71 fix: checkpoint save issue in advanced dreambooth lora sdxl script (#8926) 
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul 1b5d74a9e3 [Training] SD3 training fixes (#8917) 
* SD3 training fixes

Co-authored-by: bghira <59658056+bghira@users.noreply.github.com>

* rewrite noise addition part to respect the eqn.

* styler

* Update examples/dreambooth/README_sd3.md

Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>

---------

Co-authored-by: bghira <59658056+bghira@users.noreply.github.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul 11307ce964 [Core] remove resume_download from Hub related stuff (#8648) 
* remove resume_download

* fix: _fetch_index_file call.

* remove resume_download from docs.
 2024-12-23 13:02:14 +05:30
Tolga Cangöz a4a5a43ef9 Fix multi-gpu case for train_cm_ct_unconditional.py (#8653) 
* Fix multi-gpu case

* Prefer previously created `unwrap_model()` function

For `torch.compile()` generalizability

* `chore: update unwrap_model() function to use accelerator.unwrap_model()`
 2024-12-23 13:02:14 +05:30
ustcuna 82a13745a0 [Community Pipelines] Accelerate inference of AnimateDiff by IPEX on CPU (#8643) 
* add animatediff_ipex community pipeline

* address the 1st round review comments
 2024-12-23 13:02:14 +05:30
Tolga Cangöz 8e64c7f9a5 Remove unnecessary lines (#8569) 
* Remove unused line


---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
apolinário 67b04c891d Improve model card for push_to_hub trainers (#8697) 
* Improve trainer model cards

* Update train_dreambooth_sd3.py

* Update train_dreambooth_lora_sd3.py

* add link to adapters loading doc

* Update train_dreambooth_lora_sd3.py

---------

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Dhruv Nair 1f221b0cf9 Fix saving text encoder weights and kohya weights in advanced dreambooth lora script (#8766) 
* update

* update

* update
 2024-12-23 13:02:14 +05:30
Thomas Eding fe85e9c4f8 Add vae_roundtrip.py example (#7104) 
* Add vae_roundtrip.py example

* Add cuda support to vae_roundtrip

* Move vae_roundtrip.py into research_projects/vae

* Fix channel scaling in vae roundrip and also support taesd.

* Apply ruff --fix for CI gatekeep check

---------

Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Linoy Tsaban de14a194eb [advanced dreambooth lora] add clip_skip arg (#8715) 
* add clip_skip

* style

* smol fix

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul 63d5de4846 Update README.md to include Colab link (#8775) 2024-12-23 13:02:14 +05:30
Sayak Paul 3ca7f09a09 Allow SD3 DreamBooth LoRA fine-tuning on a free-tier Colab (#8762) 
* add experimental scripts to train SD3 transformer lora on colab

* add readme

* add colab

* Apply suggestions from code review

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

* fix link in the notebook.

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2024-12-23 13:02:14 +05:30
Sayak Paul 11c5f6bfcd Revert "[LoRA] introduce LoraBaseMixin to promote reusability." (#8773) 
Revert "[LoRA] introduce `LoraBaseMixin` to promote reusability. (#8670)"

This reverts commit a2071a1837.
 2024-12-23 13:02:14 +05:30
Sayak Paul 2686552727 [LoRA] introduce LoraBaseMixin to promote reusability. (#8670) 
* introduce  to promote reusability.

* up

* add more tests

* up

* remove comments.

* fix fuse_nan test

* clarify the scope of fuse_lora and unfuse_lora

* remove space
 2024-12-23 13:02:13 +05:30
Dhruv Nair c586a8faff Fix indent in dreambooth lora advanced SD 15 script (#8753) 
update
 2024-12-23 13:02:13 +05:30
Sayak Paul f5f9f9c083 [Tests] add test suite for SD3 DreamBooth (#8650) 
* add a test suite for SD3 DreamBooth

* lora suite

* style

* add checkpointing tests for LoRA

* add test to cover train_text_encoder.
 2024-12-23 13:02:13 +05:30
Álvaro Somoza 4d12d764f0 [SD3 LoRA Training] Fix errors when not training text encoders (#8743) 
* fix

* fix things.

Co-authored-by: Linoy Tsaban <linoy.tsaban@gmail.com>

* remove patch

* apply suggestions

---------

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <linoy.tsaban@gmail.com>
 2024-12-23 13:02:13 +05:30
WenheLI 7b3b87f45f fix the LR schedulers for dreambooth_lora (#8510) 
* update training

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2024-12-23 13:02:13 +05:30
Bhavay Malhotra 19a53baeba [train_controlnet_sdxl.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env (#8476) 
* Create diffusers.yml

* num_train_epochs

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Álvaro Somoza 29884169ad [Community pipeline] SD3 Differential Diffusion Img2Img Pipeline (#8679) 
* new pipeline
 2024-12-23 13:02:13 +05:30
Linoy Tsaban 94b734163a [Advanced dreambooth lora] adjustments to align with canonical script (#8406) 
* minor changes

* minor changes

* minor changes

* minor changes

* minor changes

* minor changes

* minor changes

* fix

* fix

* aligning with blora script

* aligning with blora script

* aligning with blora script

* aligning with blora script

* aligning with blora script

* remove prints

* style

* default val

* license

* move save_model_card to outside push_to_hub

* Update train_dreambooth_lora_sdxl_advanced.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Linoy Tsaban f8c8daa0ae [Sd3 Dreambooth LoRA] Add text encoder training for the clip encoders (#8630) 
* add clip text-encoder training

* no dora

* text encoder traing fixes

* text encoder traing fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* text encoder training fixes

* add text_encoder layers to save_lora

* style

* fix imports

* style

* fix text encoder

* review changes

* review changes

* review changes

* minor change

* add lora tag

* style

* add readme notes

* add tests for clip encoders

* style

* typo

* fixes

* style

* Update tests/lora/test_lora_layers_sd3.py

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

* Update examples/dreambooth/README_sd3.md

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

* minor readme change

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Hammond Liu 6f922c2a91 Fix redundant pipe init in sd3 lora (#8680) 
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Tolga Cangöz 58496f6ab4 Errata - Update class method convention to use cls (#8574) 
* Class methods are supposed to use `cls` conventionally

* `make style && make quality`

* An Empty commit

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Tolga Cangöz f6172748c6 Errata - Fix typos and improve style (#8571) 
* Fix typos

* Fix typos & up style

* chore: Update numbers

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Tolga Cangöz 1ced1c40d8 Discourage using deprecated revision parameter (#8573) 
* Discourage using `revision`

* `make style && make quality`

* Refactor code to use 'variant' instead of 'revision'

* `revision="bf16"` -> `variant="bf16"`

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Tolga Cangöz 2c56360222 Errata - Trim trailing white space in the whole repo (#8575) 
* Trim all the trailing white space in the whole repo

* Remove unnecessary empty places

* make style && make quality

* Trim trailing white space

* trim

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Tolga Cangöz c20d0ec72d Errata - Fix typos & improve contributing page (#8572) 
* Fix typos & improve contributing page

* `make style && make quality`

* fix typos

* Fix typo

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Vinh H. Pham 74acd0fb64 [train_lcm_distill_lora_sdxl.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env (#8446) 
fix num_train_epochs

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
drhead 33646098f5 Add extra performance features for EMAModel, torch._foreach operations and better support for non-blocking CPU offloading (#7685) 
* Add support for _foreach operations and non-blocking to EMAModel

* default foreach to false

* add non-blocking EMA offloading to SD1.5 T2I example script

* fix whitespace

* move foreach to cli argument

* linting

* Update README.md re: EMA weight training

* correct args.foreach_ema

* add tests for foreach ema

* code quality

* add foreach to from_pretrained

* default foreach false

* fix linting

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: drhead <a@a.a>
 2024-12-23 13:02:13 +05:30
Sayak Paul 22ebb0ab89 [LoRA] get rid of the legacy lora remnants and make our codebase lighter (#8623) 
* get rid of the legacy lora remnants and make our codebase lighter

* fix depcrecated lora argument

* fix

* empty commit to trigger ci

* remove print

* empty
 2024-12-23 13:02:13 +05:30
satani99 492900099c Update train_dreambooth_lora_sd3.py (#8600) 
* Update train_dreambooth_lora_sd3.py

* Update train_dreambooth_lora_sd3.py

* Update train_dreambooth_sd3.py

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2024-12-23 13:02:13 +05:30
Sayak Paul af2763cf1a Change the default weighting_scheme in the SD3 scripts (#8639) 
* change to logit_normal as the weighting scheme

* sensible default mote
 2024-12-23 13:02:13 +05:30
Sayak Paul 6ad6c79fc7 [LoRA] training fix the position of param casting when loading them (#8460) 
fix the position of param casting when loading them
 2024-12-23 13:02:13 +05:30
Sayak Paul 2fad608d8e [SD3 training] refactor the density and weighting utilities. (#8591) 
refactor the density and weighting utilities.
 2024-12-23 13:02:13 +05:30
Bagheera acfcfd3003 SD3: update default training timestep / loss weighting distribution to logit_normal (#8592) 
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
 2024-12-23 13:02:13 +05:30