GitLab

We already set the unet to requires grad false at line 506
Co-authored-by: Aryan <aryan@huggingface.co>

Remove the FP32 Wrapper
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* enable dreambooth_lora on other devices
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* enable xpu
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* check cuda device before empty cache
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* fix comment
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* import free_memory
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

---------
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

change licensing to 2025 from 2024.

* bugfix for npu not support float64

* is_mps is_npu

---------
Co-authored-by: 白超 <baichao19@huawei.com>
Co-authored-by: hlky <hlky@hlky.ac>

set rest of the blocks with requires_grad False.

* implementing flux on TPUs with ptxla

* add xla flux attention class

* run make style/quality

* Update src/diffusers/models/attention_processor.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/attention_processor.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* run style and quality

---------
Co-authored-by: Juan Acevedo <jfacevedo@google.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

Co-authored-by: J石页 <jiangshuo9@h-partners.com>

* Update rerender_a_video.py

* Update rerender_a_video.py

* Update examples/community/rerender_a_video.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update rerender_a_video.py

* make style

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

* Use Pipelines without unet

* unet.config.in_channels

* default_sample_size

* is_unet_version_less_0_9_0

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

add to readme about hf login and wandb installation to address https://github.com/huggingface/diffusers/issues/10142#issuecomment-2571655570

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

* Update rerender_a_video.py

* Update rerender_a_video.py

* Update examples/community/rerender_a_video.py
Co-authored-by: hlky <hlky@hlky.ac>

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

* dont assume scheduler has optional config params

* make style, make fix-copies

* calculate_shift

* fix-copies, usage in pipelines

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

* fix for #7365, prevent pipelines from overriding provided prompt embeds

* fix-copies

* fix implementation

* update

---------
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>

Add 5 Notebooks for Diffusers Community
Pipelines.

* Use pipelines without vae

* getattr

* vqvae

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

RFInversionFluxPipeline, small fix for enable_model_cpu_offload & enable_sequential_cpu_offload compatibility (#10480)

RFInversionFluxPipeline.encode_image, device fix

Use self._execution_device instead of self.device when selecting
a device for the input image tensor.

This allows for compatibility with enable_model_cpu_offload &
enable_sequential_cpu_offload
Co-authored-by: Teriks <Teriks@users.noreply.github.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.4 to 3.1.5.
- [Release notes](https://github.com/pallets/jinja/releases)
- [Changelog](https://github.com/pallets/jinja/blob/main/CHANGES.rst)
- [Commits](https://github.com/pallets/jinja/compare/3.1.4...3.1.5

)

---
updated-dependencies:
- dependency-name: jinja2
  dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

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

* make base code changes referred from train_instructpix2pix script in examples

* change code to use PEFT as discussed in issue 10062

* update README training command

* update README training command

* refactor variable name and freezing unet

* Update examples/research_projects/instructpix2pix_lora/train_instruct_pix2pix_lora.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* update README installation instructions.

* cleanup code using make style and quality

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

* qol improvements to the Flux script.

* propagate the dataloader changes.

Regarding the RunwayML path for V1.5 did change to stable-diffusion-v1-5/[stable-diffusion-v1-5/ stable-diffusion-inpainting] (#10476)

* Update pipeline_controlnet.py

* Update pipeline_controlnet_img2img.py

runwayml Take-down so change all from to this
stable-diffusion-v1-5/stable-diffusion-v1-5

* Update pipeline_controlnet_inpaint.py

* runwayml take-down make change to sd-legacy

* runwayml take-down make change to sd-legacy

* runwayml take-down make change to sd-legacy

* runwayml take-down make change to sd-legacy

* Update convert_blipdiffusion_to_diffusers.py

style change

Update rerender_a_video.py

* Update rerender_a_video.py

* Update rerender_a_video.py

* make style

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

Enable VAE hash to be able to change with args change. If not, train_dataset_with_embeddiings may have row number inconsistency with train_dataset_with_vae.
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

Add correct number of channels when resuming from checkpoint for Flux Control LoRa training (#10422)

* Add correct number of channels when resuming from checkpoint

* Fix Formatting

* add ds support to lora sd3.
Co-authored-by: leisuzz <jiangshuonb@gmail.com>

* style.

---------
Co-authored-by: leisuzz <jiangshuonb@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* fix: registration of out_channels in the control flux scripts.

* free memory.

* post release 0.32.0

* stylew

* sana lora training tests and misc.

* remove push to hub

* Update examples/dreambooth/train_dreambooth_lora_sana.py
Co-authored-by: Aryan <aryan@huggingface.co>

---------
Co-authored-by: Aryan <aryan@huggingface.co>

Update README_sana.md to update the default model

fix: reamde -> readme

* Use `torch` in `get_2d_rotary_pos_embed`

* Add deprecation

* feat: lora support for SANA.

* make fix-copies

* rename test class.

* attention_kwargs -> cross_attention_kwargs.

* Revert "attention_kwargs -> cross_attention_kwargs."

This reverts commit 23433bf9bccc12e0f2f55df26bae58a894e8b43b.

* exhaust 119 max line limit

* sana lora fine-tuning script.

* readme

* add a note about the supported models.

* Apply suggestions from code review
Co-authored-by: Aryan <aryan@huggingface.co>

* style

* docs for attention_kwargs.

* remove lora_scale from pag pipeline.

* copy fix

---------
Co-authored-by: Aryan <aryan@huggingface.co>

fix: fix typo that cause error

* Add offload option in flux-control training

* Update examples/flux-control/train_control_flux.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* modify help message

* fix format

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

* add decay

* add decay

* style

* Remove `negative_*` from SDXL callback

* Change example and add XL version

* update

* add

* update

* add control-lora conversion script; make flux loader handle norms; fix rank calculation assumption

* control lora updates

* remove copied-from

* create separate pipelines for flux control

* make fix-copies

* update docs

* add tests

* fix

* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* remove control lora changes

* apply suggestions from review

* Revert "remove control lora changes"

This reverts commit 73cfc519c9b99b7dc3251cc6a90a5db3056c4819.

* update

* update

* improve log messages

* updates.

* updates

* support register_config.

* fix

* fix

* fix

* updates

* updates

* updates

* fix-copies

* fix

* apply suggestions from review

* add tests

* remove conversion script; enable on-the-fly conversion

* bias -> lora_bias.

* fix-copies

* peft.py

* fix lora conversion

* changes
Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>

* fix-copies

* updates for tests

* fix

* alpha_pattern.

* add a test for varied lora ranks and alphas.

* revert changes in num_channels_latents = self.transformer.config.in_channels // 8

* revert moe

* add a sanity check on unexpected keys when loading norm layers.

* contro lora.

* fixes

* fixes

* fixes

* tests

* reviewer feedback

* fix

* proper peft version for lora_bias

* fix-copies

* updates

* updates

* updates

* remove debug code

* update docs

* integration tests

* nis

* fuse and unload.

* fix

* add slices.

* more updates.

* button up readme

* train()

* add full fine-tuning version.

* fixes

* Apply suggestions from code review
Co-authored-by: Aryan <aryan@huggingface.co>

* set_grads_to_none remove.

* readme

---------
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: yiyixuxu <yixu310@gmail.com>
Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>