Commits · 9dcac8305749de1eea84dcc53367bfac9b2bc35b · renzhc / diffusers_dcu

01 Nov, 2024 1 commit

NPU Adaption for FLUX (#9751) · 9dcac830

Leo Jiang authored Oct 31, 2024



* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

* NPU implementation for FLUX

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

9dcac830

31 Oct, 2024 8 commits

[Model Card] standardize advanced diffusion training sd15 lora (#7613) · c7543184

Abhipsha Das authored Oct 31, 2024



* modelcard generation edit

* add missed tag

* fix param name

* fix var

* change str to dict

* add use_dora check

* use correct tags for lora

* make style && make quality

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

c7543184

Revert "[LoRA] fix: lora loading when using with a device_mapped mode… (#9823) · d2e5cb3c
YiYi Xu authored Oct 31, 2024
```
Revert "[LoRA] fix: lora loading when using with a device_mapped model. (#9449)"

This reverts commit 41e4779d.
```
d2e5cb3c

[LoRA] fix: lora loading when using with a device_mapped model. (#9449) · 41e4779d

Sayak Paul authored Oct 31, 2024



* fix: lora loading when using with a device_mapped model.

* better attibutung

* empty
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* Apply suggestions from code review
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>

* minors

* better error messages.

* fix-copies

* add: tests, docs.

* add hardware note.

* quality

* Update docs/source/en/training/distributed_inference.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* fixes

* skip properly.

* fixes

---------
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
Co-authored-by: Marc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

41e4779d

[CI] add a big GPU marker to run memory-intensive tests separately on CI (#9691) · ff182ad6

Sayak Paul authored Oct 31, 2024



* add a marker for big gpu tests

* update

* trigger on PRs temporarily.

* onnx

* fix

* total memory

* fixes

* reduce memory threshold.

* bigger gpu

* empty

* g6e

* Apply suggestions from code review

* address comments.

* fix

* fix

* fix

* fix

* fix

* okay

* further reduce.

* updates

* remove

* updates

* updates

* updates

* updates

* fixes

* fixes

* updates.

* fix

* workflow fixes.

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

ff182ad6

[Tests] clean up and refactor gradient checkpointing tests (#9494) · 4adf6aff
Sayak Paul authored Oct 31, 2024
```
* check.

* fixes

* fixes

* updates

* fixes

* fixes
```
4adf6aff

[training] use the lr when using 8bit adam. (#9796) · 8ce37ab0

Sayak Paul authored Oct 31, 2024



* use the lr when using 8bit adam.

* remove lr as we pack it in params_to_optimize.

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

8ce37ab0

[training] fixes to the quantization training script and add AdEMAMix... · 09b8aebd

Sayak Paul authored Oct 31, 2024

[training] fixes to the quantization training script and add AdEMAMix optimizer as an option (#9806)

* fixes

* more fixes.

09b8aebd

[CI] add new runner for testing (#9699) · c1d4a0dd
Sayak Paul authored Oct 31, 2024
```
new runner.
```
c1d4a0dd

30 Oct, 2024 1 commit
- Allegro VAE fix (#9811) · 9a92b817
  Aryan authored Oct 30, 2024
```
fix
```
  9a92b817
29 Oct, 2024 1 commit

[core] Allegro T2V (#9736) · 0d1d267b

Aryan authored Oct 29, 2024



* update

* refactor transformer part 1

* refactor part 2

* refactor part 3

* make style

* refactor part 4; modeling tests

* make style

* refactor part 5

* refactor part 6

* gradient checkpointing

* pipeline tests (broken atm)

* update

* add coauthor
Co-Authored-By: Huan Yang <hyang@fastmail.com>

* refactor part 7

* add docs

* make style

* add coauthor
Co-Authored-By: YiYi Xu <yixu310@gmail.com>

* make fix-copies

* undo unrelated change

* revert changes to embeddings, normalization, transformer

* refactor part 8

* make style

* refactor part 9

* make style

* fix

* apply suggestions from review

* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* update example

* remove attention mask for self-attention

* update

* copied from

* update

* update

---------
Co-authored-by: Huan Yang <hyang@fastmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

0d1d267b

28 Oct, 2024 5 commits

adds the pipeline for pixart alpha controlnet (#8857) · c5376c56

Raul Ciotescu authored Oct 28, 2024



* add the controlnet pipeline for pixart alpha

---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: junsongc <cjs1020440147@icloud.com>

c5376c56

[flux dreambooth lora training] make LoRA target modules configurable + small bug fix (#9646) · 743a5697

Linoy Tsaban authored Oct 28, 2024

* make lora target modules configurable and change the default

* style

* make lora target modules configurable and change the default

* fix bug when using prodigy and training te

* fix mixed precision training as  proposed in https://github.com/huggingface/diffusers/pull/9565

 for full dreambooth as well

* add test and notes

* style

* address sayaks comments

* style

* fix test

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

743a5697

[SD 3.5 Dreambooth LoRA] support configurable training block & layers (#9762) · db5b6a96

Linoy Tsaban authored Oct 28, 2024

* configurable layers

* configurable layers

* update README

* style

* add test

* style

* add layer test, update readme, add nargs

* readme

* test style

* remove print, change nargs

* test arg change

* style

* revert nargs 2/2

* address sayaks comments

* style

* address sayaks comments

db5b6a96

[Fix] remove setting lr for T5 text encoder when using prodigy in flux... · 493aa743

Biswaroop authored Oct 28, 2024


[Fix] remove setting lr for T5 text encoder when using prodigy in flux dreambooth lora script (#9473)

* fix: removed setting of text encoder lr for T5 as it's not being tuned

* fix: removed setting of text encoder lr for T5 as it's not being tuned

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

493aa743

[Fix] train_dreambooth_lora_flux_advanced ValueError: unexpected save model:... · 3b5b1c56

Vinh H. Pham authored Oct 28, 2024

[Fix] train_dreambooth_lora_flux_advanced ValueError: unexpected save model: <class 'transformers.models.t5.modeling_t5.T5EncoderModel'> (#9777)

fix save state te T5

3b5b1c56

26 Oct, 2024 1 commit
- [research_projects] Update README.md to include a note about NF5 T5-xxl (#9775) · fddbab79
  Sayak Paul authored Oct 26, 2024
```
Update README.md
```
  fddbab79
25 Oct, 2024 6 commits

Added Support of Xlabs controlnet to FluxControlNetInpaintPipeline (#9770) · 298ab6eb
SahilCarterr authored Oct 26, 2024
```
* added xlabs support
```
298ab6eb
[refactor] enhance readability of flux related pipelines (#9711) · 73b59f52
Ina authored Oct 26, 2024
```
* flux pipline: readability enhancement.
```
73b59f52

Add a doc for AWS Neuron in Diffusers (#9766) · 52d44498

Jingya HUANG authored Oct 25, 2024



* start draft

* add doc

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* bref intro of ON

* Update docs/source/en/optimization/neuron.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

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

52d44498

[research_projects] add flux training script with quantization (#9754) · df073ba1
Sayak Paul authored Oct 26, 2024
```
* add flux training script with quantization

* remove exclamation
```
df073ba1

[bugfix] bugfix for npu free memory (#9640) · 94643fac

Leo Jiang authored Oct 25, 2024



* Improve NPU performance

* Improve NPU performance

* Improve NPU performance

* Improve NPU performance

* [bugfix] bugfix for npu free memory

* [bugfix] bugfix for npu free memory

* [bugfix] bugfix for npu free memory

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

94643fac

[Docs] fix docstring typo in SD3 pipeline (#9765) · 435f6b7e
Zhiyang Shen authored Oct 25, 2024
```
* fix docstring typo in SD3 pipeline

* fix docstring typo in SD3 pipeline
```
435f6b7e

24 Oct, 2024 1 commit
- Some minor updates to the nightly and push workflows (#9759) · 1d1e1a28
  Sayak Paul authored Oct 24, 2024
```
* move lora integration tests to nightly./

* remove slow marker in the workflow where not needed.
```
  1d1e1a28
23 Oct, 2024 4 commits
- config attribute not foud error for FluxImagetoImage Pipeline for multi controlnet solved (#9586) · 24c7d578
  Rachit Shah authored Oct 24, 2024
```
Co-authored-by: YiYi Xu <yixu310@gmail.com>
```
  24c7d578
- [SD3-5 dreambooth lora] update model cards (#9749) · bfa0aa4f
  Linoy Tsaban authored Oct 23, 2024
```
* improve readme

* style

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
```
  bfa0aa4f
- [Official callbacks] SDXL Controlnet CFG Cutoff (#9311) · ab1b7b20
  Álvaro Somoza authored Oct 23, 2024
```
* initial proposal

* style
```
  ab1b7b20
- fix bug in `require_accelerate_version_greater` (#9746) · 9366c8f8
  Fanli Lin authored Oct 23, 2024
```
fix bug
```
  9366c8f8
22 Oct, 2024 7 commits
- post-release 0.31.0 (#9742) · e45c25d0
  Sayak Paul authored Oct 22, 2024
```
* post-release

* style
```
  e45c25d0
- is_safetensors_compatible fix (#9741) · 76c00c72
  Dhruv Nair authored Oct 22, 2024
```
update
```
  76c00c72
- Fix typos (#9739) · 0d9d98fe
  Dhruv Nair authored Oct 22, 2024
```
* update

* update

* update

* update

* update

* update
```
  0d9d98fe
- [bitsandbbytes] follow-ups (#9730) · 60ffa842
  Sayak Paul authored Oct 22, 2024
```
* bnb follow ups.

* add a warning when dtypes mismatch.

* fx-copies

* clear cache.

* check_if_quantized_param

* add a check on shape.

* updates

* docs

* improve readability.

* resources.

* fix
```
  60ffa842
- [Fix] Using sharded checkpoints with gated repositories (#9737) · 0f079b93
  Álvaro Somoza authored Oct 22, 2024
```
fix
```
  0f079b93
- Update sd3 controlnet example (#9735) · b0ffe922
  Yu Zheng authored Oct 21, 2024
```
* use make_image_grid in diffusers.utils

* use checkpoint on the Hub
```
  b0ffe922
- Fix `schedule_shifted_power` usage in 🪆Matryoshka Diffusion Models (#9723) · 1b64772b
  Tolga Cangöz authored Oct 22, 2024
```
* [matryoshka.py] Add schedule_shifted_power attribute and update get_schedule_shifted method
```
  1b64772b
21 Oct, 2024 5 commits

fix singlestep dpm tests (#9716) · 2d280f17
YiYi Xu authored Oct 21, 2024
```
fix
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
```
2d280f17

[bugfix] reduce float value error when adding noise (#9004) · 63a0c9e5

G.O.D authored Oct 22, 2024



* Update train_controlnet.py

reduce float value error for bfloat16

* Update train_controlnet_sdxl.py

* style

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>

63a0c9e5

minor doc/test update (#9734) · e2d037bb

YiYi Xu authored Oct 21, 2024



* update some docs and tests!

---------
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: apolinário <joaopaulo.passos@gmail.com>

e2d037bb

[docs] add docstrings in `pipline_stable_diffusion.py` (#9590) · bcd61fd3

timdalxx authored Oct 22, 2024



* fix the issue on flux dreambooth lora training

* update : origin main code

* docs: update pipeline_stable_diffusion docstring

* docs: update pipeline_stable_diffusion docstring

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* fix: style

* fix: style

* fix: copies

* make fix-copies

* remove extra newline

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

bcd61fd3

[Docs] docs to xlabs controlnets. (#9688) · d27ecc59

Sayak Paul authored Oct 21, 2024



* docs to xlabs controlnets.
Co-authored-by: Anzhella Pankratova <son0shad@gmail.com>

* Apply suggestions from code review
Co-authored-by: Anzhella Pankratova <54744846+Anghellia@users.noreply.github.com>

---------
Co-authored-by: Anzhella Pankratova <son0shad@gmail.com>
Co-authored-by: Anzhella Pankratova <54744846+Anghellia@users.noreply.github.com>

d27ecc59