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
5,896 Commits 740 Branches 94 Tags
version-checks-cache
Commit Graph

1241 Commits

Author SHA1 Message Date
Quentin Gallouédec
c8bb1ff53e Use HF Papers (#11567) 
* Use HF Papers

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-05-19 06:22:33 -10:00
Kenneth Gerald Hamilton
07dd6f8c0e [train_dreambooth.py] Fix the LR Schedulers when num_train_epochs is passed in a distributed training env (#11239) 
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-05-13 07:34:01 +05:30
Abdellah Oumida
ddd0cfb497 Fix typo in train_diffusion_orpo_sdxl_lora_wds.py (#11541) 2025-05-12 15:28:29 -10:00
scxue
784db0eaab Add cross attention type for Sana-Sprint training in diffusers. (#11514) 
* test permission

* Add cross attention type for Sana-Sprint.

* Add Sana-Sprint training script in diffusers.

* make style && make quality;

* modify the attention processor with `set_attn_processor` and change `SanaAttnProcessor3_0` to `SanaVanillaAttnProcessor`

* Add import for SanaVanillaAttnProcessor

* Add README file.

* Apply suggestions from code review

* style

* Update examples/research_projects/sana/README.md

---------

Co-authored-by: lawrence-cj <cjs1020440147@icloud.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-05-08 18:55:29 +05:30
Linoy Tsaban
66e50d4e24 [LoRA] make lora alpha and dropout configurable (#11467) 
* add lora_alpha and lora_dropout

* Apply style fixes

* add lora_alpha and lora_dropout

* Apply style fixes

* revert lora_alpha until #11324 is merged

* Apply style fixes

* empty commit

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-05-08 11:54:50 +03:00
RogerSinghChugh
ed4efbd63d Update training script for txt to img sdxl with lora supp with new interpolation. (#11496) 
* Update training script for txt to img sdxl with lora supp with new interpolation.

* ran make style and make quality.
 2025-05-05 12:33:28 -04:00
Yijun Lee
9c29e938d7 Set LANCZOS as the default interpolation method for image resizing. (#11492) 
* Set LANCZOS as the default interpolation method for image resizing.

* style: run make style and quality checks
 2025-05-05 12:18:40 -04:00
Sayak Paul
071807c853 [training] feat: enable quantization for hidream lora training. (#11494) 
* feat: enable quantization for hidream lora training.

* better handle compute dtype.

* finalize.

* fix dtype.

---------

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-05-05 20:44:35 +05:30
Evan Han
ee1516e5c7 [train_dreambooth_lora_lumina2] Add LANCZOS as the default interpolation mode for image resizing (#11491) 
[ADD] interpolation
 2025-05-05 10:41:33 -04:00
MinJu-Ha
ec9323996b [train_dreambooth_lora_sdxl] Add --image_interpolation_mode option for image resizing (default to lanczos) (#11490) 
feat(train_dreambooth_lora_sdxl): support --image_interpolation_mode with default to lanczos
 2025-05-05 10:19:30 -04:00
Parag Ekbote
fc5e906689 [train_text_to_image_sdxl]Add LANCZOS as default interpolation mode for image resizing (#11455) 
* Add LANCZOS as default interplotation mode.

* update script

* Update as per code review.

* make style.
 2025-05-05 09:52:19 -04:00
Yash
ec3d58286d [train_dreambooth_lora_flux_advanced] Add LANCZOS as the default interpolation mode for image resizing (#11472) 
* [train_controlnet_sdxl] Add LANCZOS as the default interpolation mode for image resizing

* [train_dreambooth_lora_flux_advanced] Add LANCZOS as the default interpolation mode for image resizing
 2025-05-02 18:14:41 -04:00
Yuanzhou
ed6cf52572 [train_dreambooth_lora_sdxl_advanced] Add LANCZOS as the default interpolation mode for image resizing (#11471) 2025-05-02 16:46:01 -04:00
co63oc
86294d3c7f Fix typos in docs and comments (#11416) 
* Fix typos in docs and comments

* Apply style fixes

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-30 20:30:53 -10:00
Vaibhav Kumawat
daf0a23958 Add LANCZOS as default interplotation mode. (#11463) 
* Add LANCZOS as default interplotation mode.

* LANCZOS as default interplotation

* LANCZOS as default interplotation mode

* Added LANCZOS as default interplotation mode
 2025-04-30 14:22:38 -04:00
captainzz
8cd7426e56 Add StableDiffusion3InstructPix2PixPipeline (#11378) 
* upload StableDiffusion3InstructPix2PixPipeline

* Move to community

* Add readme

* Fix images

* remove images

* Change image url

* fix

* Apply style fixes
 2025-04-30 06:13:12 -04:00
Youlun Peng
58431f102c Set LANCZOS as the default interpolation for image resizing in ControlNet training (#11449) 
Set LANCZOS as the default interpolation for image resizing
 2025-04-29 08:47:02 -04:00
Linoy Tsaban
0ac1d5b482 [Hi-Dream LoRA] fix bug in validation (#11439) 
remove unnecessary pipeline moving to cpu in validation

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-28 06:22:32 -10:00
tongyu
3da98e7ee3 [train_text_to_image_lora] Better image interpolation in training scripts follow up (#11427) 
* Update train_text_to_image_lora.py

* update_train_text_to_image_lora
 2025-04-28 11:23:24 -04:00
tongyu
b3b04fefde [train_text_to_image] Better image interpolation in training scripts follow up (#11426) 
* Update train_text_to_image.py

* update
 2025-04-28 10:50:33 -04:00
Mert Erbak
bd96a084d3 [train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing (#11421) 
* Set LANCZOS as default interpolation mode for resizing

* [train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing
 2025-04-26 01:58:41 -04:00
co63oc
f00a995753 Fix typos in strings and comments (#11407) 2025-04-24 08:53:47 -10:00
Linoy Tsaban
edd7880418 [HiDream LoRA] optimizations + small updates (#11381) 
* 1. add pre-computation of prompt embeddings when custom prompts are used as well
2. save model card even if model is not pushed to hub
3. remove scheduler initialization from code example - not necessary anymore (it's now if the base model's config)
4. add skip_final_inference - to allow to run with validation, but skip the final loading of the pipeline with the lora weights to reduce memory reqs

* pre encode validation prompt as well

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

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

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

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

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

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

* pre encode validation prompt as well

* Apply style fixes

* empty commit

* change default trained modules

* empty commit

* address comments + change encoding of validation prompt (before it was only pre-encoded if custom prompts are provided, but should be pre-encoded either way)

* Apply style fixes

* empty commit

* fix validation_embeddings definition

* fix final inference condition

* fix pipeline deletion in last inference

* Apply style fixes

* empty commit

* layers

* remove readme remarks on only pre-computing when instance prompt is provided and change example to 3d icons

* smol fix

* empty commit

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-24 07:48:19 +03:00
Teriks
b4be42282d Kolors additional pipelines, community contrib (#11372) 
* Kolors additional pipelines, community contrib

---------

Co-authored-by: Teriks <Teriks@users.noreply.github.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-04-23 11:07:27 -10:00
Ishan Dutta
4b60f4b602 [train_dreambooth_flux] Add LANCZOS as the default interpolation mode for image resizing (#11395) 2025-04-23 10:47:05 -04:00
Ameer Azam
026507c06c Update README_hidream.md (#11386) 
Small change
requirements_sana.txt to 
requirements_hidream.txt
 2025-04-22 20:08:26 -04:00
Linoy Tsaban
e30d3bf544 [LoRA] add LoRA support to HiDream and fine-tuning script (#11281) 
* initial commit

* initial commit

* initial commit

* initial commit

* initial commit

* initial commit

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

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

* move prompt embeds, pooled embeds outside

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

Co-authored-by: hlky <hlky@hlky.ac>

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

Co-authored-by: hlky <hlky@hlky.ac>

* fix import

* fix import and tokenizer 4, text encoder 4 loading

* te

* prompt embeds

* fix naming

* shapes

* initial commit to add HiDreamImageLoraLoaderMixin

* fix init

* add tests

* loader

* fix model input

* add code example to readme

* fix default max length of text encoders

* prints

* nullify training cond in unpatchify for temp fix to incompatible shaping of transformer output during training

* smol fix

* unpatchify

* unpatchify

* fix validation

* flip pred and loss

* fix shift!!!

* revert unpatchify changes (for now)

* smol fix

* Apply style fixes

* workaround moe training

* workaround moe training

* remove prints

* to reduce some memory, keep vae in `weight_dtype` same as we have for flux (as it's the same vae)
bbd0c161b5/examples/dreambooth/train_dreambooth_lora_flux.py (L1207)

* refactor to align with HiDream refactor

* refactor to align with HiDream refactor

* refactor to align with HiDream refactor

* add support for cpu offloading of text encoders

* Apply style fixes

* adjust lr and rank for train example

* fix copies

* Apply style fixes

* update README

* update README

* update README

* fix license

* keep prompt2,3,4 as None in validation

* remove reverse ode comment

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

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

* Update examples/dreambooth/train_dreambooth_lora_hidream.py

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

* vae offload change

* fix text encoder offloading

* Apply style fixes

* cleaner to_kwargs

* fix module name in copied from

* add requirements

* fix offloading

* fix offloading

* fix offloading

* update transformers version in reqs

* try AutoTokenizer

* try AutoTokenizer

* Apply style fixes

* empty commit

* Delete tests/lora/test_lora_layers_hidream.py

* change tokenizer_4 to load with AutoTokenizer as well

* make text_encoder_four and tokenizer_four configurable

* save model card

* save model card

* revert T5

* fix test

* remove non diffusers lumina2 conversion

---------

Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com>
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-22 11:44:02 +03:00
PromeAI
7a4a126db8 fix issue that training flux controlnet was unstable and validation r… (#11373) 
* fix issue that training flux controlnet was unstable and validation results were unstable

* del unused code pieces, fix grammar

---------

Co-authored-by: Your Name <you@example.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-21 08:16:05 -10:00
Kenneth Gerald Hamilton
0dec414d5b [train_dreambooth_lora_sdxl.py] Fix the LR Schedulers when num_train_epochs is passed in a distributed training env (#11240) 
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2025-04-21 12:51:03 +05:30
Linoy Tsaban
44eeba07b2 [Flux LoRAs] fix lr scheduler bug in distributed scenarios (#11242) 
* add fix

* add fix

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-21 10:08:45 +03:00
Kazuki Yoda
ef47726e2d Fix: StableDiffusionXLControlNetAdapterInpaintPipeline incorrectly inherited StableDiffusionLoraLoaderMixin (#11357) 
Fix: Inherit `StableDiffusionXLLoraLoaderMixin`

`StableDiffusionXLControlNetAdapterInpaintPipeline`
used to incorrectly inherit
`StableDiffusionLoraLoaderMixin`
instead of `StableDiffusionXLLoraLoaderMixin`
 2025-04-18 12:46:06 -10:00
Sayak Paul
4b868f14c1 post release 0.33.0 (#11255) 
* post release

* update

* fix deprecations

* remaining

* update

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-04-15 06:50:08 -10:00
Dhruv Nair
edc154da09 Update Ruff to latest Version (#10919) 
* update

* update

* update

* update
 2025-04-09 16:51:34 +05:30
Sayak Paul
fd02aad402 fix: SD3 ControlNet validation so that it runs on a A100. (#11238) 
* fix: SD3 ControlNet validation so that it runs on a A100.

* use backend-agnostic cache and pass devide.
 2025-04-09 12:12:53 +05:30
Linoy Tsaban
71f34fc5a4 [Flux LoRA] fix issues in flux lora scripts (#11111) 
* remove custom scheduler

* update requirements.txt

* log_validation with mixed precision

* add intermediate embeddings saving when checkpointing is enabled

* remove comment

* fix validation

* add unwrap_model for accelerator, torch.no_grad context for validation, fix accelerator.accumulate call in advanced script

* revert unwrap_model change temp

* add .module to address distributed training bug + replace accelerator.unwrap_model with unwrap model

* changes to align advanced script with canonical script

* make changes for distributed training + unify unwrap_model calls in advanced script

* add module.dtype fix to dreambooth script

* unify unwrap_model calls in dreambooth script

* fix condition in validation run

* mixed precision

* Update examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py

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

* smol style change

* change autocast

* Apply style fixes

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-08 17:40:30 +03:00
Álvaro Somoza
723dbdd363 [Training] Better image interpolation in training scripts (#11206) 
* initial

* Update examples/dreambooth/train_dreambooth_lora_sdxl.py

Co-authored-by: hlky <hlky@hlky.ac>

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
 2025-04-08 12:26:07 +05:30
Bhavay Malhotra
fbf61f465b [train_controlnet.py] Fix the LR schedulers when num_train_epochs is passed in a distributed training env (#8461) 
* Create diffusers.yml

* fix num_train_epochs

* Delete diffusers.yml

* Fixed Changes

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-04-08 12:10:09 +05:30
Edna
41afb6690c Add Wan with STG as a community pipeline (#11184) 
* Add stg wan to community pipelines

* remove debug prints

* remove unused comment

* Update doc

* Add credit + fix typo

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-05 04:00:40 +02:00
Kenneth Gerald Hamilton
f10775b1b5 Fixed requests.get function call by adding timeout parameter. (#11156) 
* Fixed requests.get function call by adding timeout parameter.

* declare DIFFUSERS_REQUEST_TIMEOUT in constants and import when needed

* remove unneeded os import

* Apply style fixes

---------

Co-authored-by: Sai-Suraj-27 <sai.suraj.27.729@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2025-04-04 07:23:14 +01:00
Abhipsha Das
d9023a671a [Model Card] standardize advanced diffusion training sdxl lora (#7615) 
* model card gen code

* push modelcard creation

* remove optional from params

* add import

* add use_dora check

* correct lora var use in tags

* make style && make quality

---------

Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-04-03 07:43:01 +05:30
Eliseu Silva
c4646a3931 feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline (#11188) 
* feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline for Image SR.

* added pipeline
 2025-04-02 11:33:19 -10:00
hlky
d6f4774c1c Add latents_mean and latents_std to SDXLLongPromptWeightingPipeline (#11034) 2025-03-31 11:32:29 -10:00
Tolga Cangöz
0213179ba8 Update README and example code for AnyText usage (#11028) 
* [Documentation] Update README and example code with additional usage instructions for AnyText

* [Documentation] Update README for AnyTextPipeline and improve logging in code

* Remove wget command for font file from example docstring in anytext.py
 2025-03-23 21:15:57 +05:30
Parag Ekbote
f424b1b062 Notebooks for Community Scripts-8 (#11128) 
Add 4 Notebooks and update the missing links for the
example README.
 2025-03-20 12:24:46 -07:00
Yuqian Hong
fc28791fc8 [BUG] Fix Autoencoderkl train script (#11113) 
* add disc_optimizer step (not fix)

* support syncbatchnorm in discriminator
 2025-03-19 16:49:02 +05:30
Juan Acevedo
27916822b2 update readme instructions. (#11096) 
Co-authored-by: Juan Acevedo <jfacevedo@google.com>
 2025-03-17 20:07:48 -10:00
Yuxuan Zhang
82188cef04 CogView4 Control Block (#10809) 
* cogview4 control training


---------

Co-authored-by: OleehyO <leehy0357@gmail.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>
 2025-03-15 07:15:56 -10:00
Juan Acevedo
6b9a3334db reverts accidental change that removes attn_mask in attn. Improves fl… (#11065) 
reverts accidental change that removes attn_mask in attn. Improves flux ptxla by using flash block sizes. Moves encoding outside the for loop.

Co-authored-by: Juan Acevedo <jfacevedo@google.com>
 2025-03-14 12:47:01 -10:00
Andreas Jörg
8ead643bb7 [examples/controlnet/train_controlnet_sd3.py] Fixes #11050 - Cast prompt_embeds and pooled_prompt_embeds to weight_dtype to prevent dtype mismatch (#11051) 
Fix: dtype mismatch of prompt embeddings in sd3 controlnet training

Co-authored-by: Andreas Jörg <andreasjoerg@MacBook-Pro-von-Andreas-2.fritz.box>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2025-03-14 17:33:15 +05:30
Yaniv Galron
5e48cd27d4 making ``formatted_images`` initialization compact (#10801) 
compact writing

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2025-03-13 09:27:14 -10:00