Commits · 798e17187d5a5fd9a44d2587938ff6a39b205254 · renzhc / diffusers_dcu

06 Feb, 2025 2 commits

[bugfix] NPU Adaption for Sana (#10724) · cd0a4a82

Leo Jiang authored Feb 06, 2025



* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* NPU Adaption for Sanna

* [bugfix]NPU Adaption for Sanna

---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

cd0a4a82

[Community] Enhanced `Model Search` (#10417) · 145522cb

suzukimain authored Feb 06, 2025

* Added `auto_load_textual_inversion` and `auto_load_lora_weights`

* update README.md

* fix

* make quality

* Fix and `make style`

145522cb

04 Feb, 2025 2 commits
- Notebooks for Community Scripts-6 (#10713) · dbe0094e
  Parag Ekbote authored Feb 04, 2025
```
* Fix Doc Tutorial.

* Add 4 Notebooks and improve their example
scripts.
```
  dbe0094e
- Fix train_text_to_image.py --help (#10711) · f63d3223
  Nicolas authored Feb 03, 2025
  
  f63d3223
31 Jan, 2025 1 commit

Fix inconsistent random transform in instruct pix2pix (#10698) · 5d2d2398

Thanh Le authored Jan 31, 2025

* Update train_instruct_pix2pix.py

Fix inconsistent random transform in instruct_pix2pix

* Update train_instruct_pix2pix_sdxl.py

5d2d2398

28 Jan, 2025 2 commits

Fix pipeline dtype unexpected change when using SDXL reference community... · 196aef5a

Dimitri Barbot authored Jan 28, 2025

Fix pipeline dtype unexpected change when using SDXL reference community pipelines in float16 mode (#10670)

Fix pipeline dtype unexpected change when using SDXL reference community pipelines

196aef5a

Refactor gradient checkpointing (#10611) · c4d4ac21

Aryan authored Jan 28, 2025

* update

* remove unused fn

* apply suggestions based on review

* update + cleanup 🧹

* more cleanup 🧹

* make fix-copies

* update test

c4d4ac21

27 Jan, 2025 3 commits

[training] Convert to ImageFolder script (#10664) · 41571773
hlky authored Jan 27, 2025
```
* [training] Convert to ImageFolder script

* make
```
41571773

Add community pipeline for semantic guidance for FLUX (#10610) · f7f36c7d

Marlon May authored Jan 27, 2025



* add community pipeline for semantic guidance for flux

* fix imports in community pipeline for semantic guidance for flux

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

* fix community pipeline for semantic guidance for flux

---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
Co-authored-by: hlky <hlky@hlky.ac>

f7f36c7d

create a script to train autoencoderkl (#10605) · 4fa24591

Yuqian Hong authored Jan 27, 2025



* create a script to train vae

* update main.py

* update train_autoencoderkl.py

* update train_autoencoderkl.py

* add a check of --pretrained_model_name_or_path and --model_config_name_or_path

* remove the comment, remove diffusers in requiremnets.txt, add validation_image ote

* update autoencoderkl.py

* quality

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

4fa24591

24 Jan, 2025 2 commits

NPU Adaption for Sanna (#10409) · 07860f99

Leo Jiang authored Jan 24, 2025



* NPU Adaption for Sanna


---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

07860f99

Add pipeline_stable_diffusion_xl_attentive_eraser (#10579) · 87252d80

Wenhao Sun authored Jan 24, 2025



* add pipeline_stable_diffusion_xl_attentive_eraser

* add pipeline_stable_diffusion_xl_attentive_eraser_make_style

* make style and add example output

* update Docs
Co-authored-by: Other Contributor <a457435687@126.com>

* add Oral
Co-authored-by: Other Contributor <a457435687@126.com>

* update_review
Co-authored-by: Other Contributor <a457435687@126.com>

* update_review_ms
Co-authored-by: Other Contributor <a457435687@126.com>

---------
Co-authored-by: Other Contributor <a457435687@126.com>

87252d80

23 Jan, 2025 1 commit

removing redundant requires_grad = False (#10628) · a451c0ed

Yaniv Galron authored Jan 23, 2025



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

a451c0ed

21 Jan, 2025 3 commits

Remove the FP32 Wrapper when evaluating (#10617) · 158a5a87

Muyang Li authored Jan 21, 2025



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

158a5a87

Enable dreambooth lora finetune example on other devices (#10602) · 012d08b1

jiqing-feng authored Jan 21, 2025



* 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>

012d08b1

[chore] change licensing to 2025 from 2024. (#10615) · 4ace7d04
Sayak Paul authored Jan 21, 2025
```
change licensing to 2025 from 2024.
```
4ace7d04

20 Jan, 2025 1 commit

bugfix for npu not support float64 (#10123) · 75a636da

baymax591 authored Jan 21, 2025



* 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>

75a636da

19 Jan, 2025 1 commit
- [training] set rest of the blocks with `requires_grad` False. (#10607) · 328e0d20
  Sayak Paul authored Jan 19, 2025
```
set rest of the blocks with requires_grad False.
```
  328e0d20
16 Jan, 2025 1 commit

implementing flux on TPUs with ptxla (#10515) · aeac0a00

Juan Acevedo authored Jan 16, 2025



* 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>

aeac0a00

15 Jan, 2025 1 commit
- [Sana 4K] Add vae tiling option to avoid OOM (#10583) · b0c89738
  Leo Jiang authored Jan 15, 2025
```
Co-authored-by: J石页 <jiangshuo9@h-partners.com>
```
  b0c89738
13 Jan, 2025 1 commit
- Fix train_dreambooth_lora_sd3_miniature (#10554) · 980736b7
  hlky authored Jan 13, 2025
  
  980736b7
10 Jan, 2025 3 commits

add the xm.mark_step for the first denosing loop (#10530) · d6c030fd

chaowenguo authored Jan 10, 2025



* 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>

d6c030fd

Use Pipelines without unet (#10440) · 12fbe3f7

hlky authored Jan 10, 2025



* 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>

12fbe3f7

small readme changes for advanced training examples (#10473) · 83ba01a3

Linoy Tsaban authored Jan 10, 2025

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>

83ba01a3

09 Jan, 2025 2 commits

add callable object to convert frame into control_frame to reduce cpu memory usage. (#10501) · 7bc8b923

chaowenguo authored Jan 09, 2025



* 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>

7bc8b923

flux: make scheduler config params optional (#10384) · f0c6d978

Vladimir Mandic authored Jan 09, 2025



* 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>

f0c6d978

08 Jan, 2025 2 commits

fix for #7365, prevent pipelines from overriding provided prompt embeds (#7926) · a0acbdc9

Bagheera authored Jan 08, 2025



* 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>

a0acbdc9

Notebooks for Community Scripts-5 (#10499) · 5655b22e
Parag Ekbote authored Jan 08, 2025
```
Add 5 Notebooks for Diffusers Community
Pipelines.
```
5655b22e

07 Jan, 2025 6 commits

Use pipelines without vae (#10441) · ee7e141d

hlky authored Jan 07, 2025



* Use pipelines without vae

* getattr

* vqvae

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

ee7e141d

RFInversionFluxPipeline, small fix for enable_model_cpu_offload &... · 03bcf5ae

Teriks authored Jan 07, 2025

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>

03bcf5ae

Bump jinja2 from 3.1.4 to 3.1.5 in /examples/research_projects/realfill (#10377) · e0b96ba7

dependabot[bot] authored Jan 07, 2025

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>

e0b96ba7

Use Pipelines without scheduler (#10439) · 628f2c54
hlky authored Jan 07, 2025
```
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
```
628f2c54

Refactor instructpix2pix lora to support peft (#10205) · f1e0c7ce

Rahul Raman authored Jan 06, 2025



* 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>

f1e0c7ce

[Training] QoL improvements in the Flux Control training scripts (#10461) · b94cfd79
Sayak Paul authored Jan 07, 2025
```
* qol improvements to the Flux script.

* propagate the dataloader changes.
```
b94cfd79

06 Jan, 2025 1 commit

Regarding the RunwayML path for V1.5 did change to... · 4f5e3e35

Ameer Azam authored Jan 07, 2025

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

4f5e3e35

04 Jan, 2025 1 commit
- Update rerender_a_video.py fix dtype error (#10451) · 4e445348
  chaowenguo authored Jan 04, 2025
```
Update rerender_a_video.py
```
  4e445348
03 Jan, 2025 1 commit

add pythor_xla support for render a video (#10443) · a17832b2

chaowenguo authored Jan 03, 2025



* Update rerender_a_video.py

* Update rerender_a_video.py

* make style

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

a17832b2

02 Jan, 2025 2 commits

Update train_text_to_image_sdxl.py (#8830) · f7822ae4

Doug J authored Jan 02, 2025



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>

f7822ae4

Add correct number of channels when resuming from checkpoint for Flux Control... · 4b9f1c7d

Dev Rajput authored Jan 02, 2025

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

4b9f1c7d

30 Dec, 2024 1 commit

[training] add ds support to lora sd3. (#10378) · 5f724735

Sayak Paul authored Dec 30, 2024



* 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>

5f724735