Skip to content

[Model Card] standardize advanced diffusion training sdxl lora #7615

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 12 commits into from
Apr 3, 2025

Conversation

chiral-carbon
Copy link
Contributor

What does this PR do?

Fixes #6891 for Advanced Diffusion Training SDXL with LoRA

Notebook example: Jupyter notebook
Example model card: Model Card

Before submitting

Who can review?

@sayakpaul @linoytsaban

@sayakpaul sayakpaul requested a review from linoytsaban April 10, 2024 03:15
Copy link
Collaborator

@linoytsaban linoytsaban left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hey @chiral-carbon! same small comment from the sd15 PR, applies here too - since it can be either a LoRA or a DoRA, we need to check if the use_dora arg is True and adapt the tag accordingly :)
other than that, all good!

@chiral-carbon
Copy link
Contributor Author

thanks @linoytsaban! have addressed the use_dora check, please review!

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

"stable-diffusion-xl-diffusers",
"text-to-image",
"diffusers",
"lora",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

last thing 😊- we need to switch "lora" -> lora in the tags here (to use the var defined in line 114)

@linoytsaban
Copy link
Collaborator

Hey @chiral-carbon! I think once we address the "lora" -> lora change it'll also pass all the tests and we can merge :)

@chiral-carbon
Copy link
Contributor Author

Hi @linoytsaban my apologies, I completely missed this message, will do it asap!

@chiral-carbon
Copy link
Contributor Author

@linoytsaban pushed it!

@linoytsaban
Copy link
Collaborator

Thanks @chiral-carbon! I'm not sure what's failing the quality tests now 🧐 could you run make fix up please?

@chiral-carbon
Copy link
Contributor Author

hi @linoytsaban this is the output of make fixup:

(hf-diff) ada@Abhipshas-MacBook-Pro diffusers % make fixup
Checking/fixing examples/advanced_diffusion_training/train_dreambooth_lora_sd15_advanced.py
Found 3 errors (3 fixed, 0 remaining).
1 file reformatted
python utils/custom_init_isort.py
python utils/check_doc_toc.py --fix_and_overwrite
running deps_table_update
updating src/diffusers/dependency_versions_table.py
python utils/check_dummies.py
python utils/check_repo.py
Traceback (most recent call last):
  File "/Users/ada/Desktop/Projects/diffusers/utils/check_repo.py", line 25, in <module>
    from diffusers.models.auto import get_values
ModuleNotFoundError: No module named 'diffusers.models.auto'
make: *** [repo-consistency] Error 1

it seems that it has no module named models.auto?

@tolgacangoz
Copy link
Contributor

Could you run make style && make quality?

@chiral-carbon
Copy link
Contributor Author

this is the output of make style && make quality:

(hf-diff) ada@Abhipshas-MacBook-Pro diffusers % make style && make quality
ruff check examples scripts src tests utils benchmarks setup.py --fix
ruff format examples scripts src tests utils benchmarks setup.py
1 file reformatted, 874 files left unchanged
doc-builder style src/diffusers docs/source --max_len 119
/Library/Developer/CommandLineTools/usr/bin/make autogenerate_code
running deps_table_update
updating src/diffusers/dependency_versions_table.py
/Library/Developer/CommandLineTools/usr/bin/make extra_style_checks
python utils/custom_init_isort.py
python utils/check_doc_toc.py --fix_and_overwrite
ruff check examples scripts src tests utils benchmarks setup.py
ruff format --check examples scripts src tests utils benchmarks setup.py
875 files left unchanged
doc-builder style src/diffusers docs/source --max_len 119 --check_only
python utils/check_doc_toc.py

have pushed it as well, it changed the formatting of the widget_dict append operation in line 124

@chiral-carbon
Copy link
Contributor Author

should I also run make test? the contributor guidelines said that it would take time to run normally so I skipped it

@chiral-carbon
Copy link
Contributor Author

hi @linoytsaban @tolgacangoz! is this PR good to be merged?

@tolgacangoz
Copy link
Contributor

tolgacangoz commented Jul 14, 2024

It seems that there are conflicts that must be resolved. Could you resolve them?

@chiral-carbon
Copy link
Contributor Author

@tolgacangoz done

Copy link
Contributor

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

@github-actions github-actions bot added the stale Issues that haven't received updates label Sep 14, 2024
@a-r-r-o-w a-r-r-o-w removed the stale Issues that haven't received updates label Oct 17, 2024
@a-r-r-o-w a-r-r-o-w requested a review from linoytsaban October 17, 2024 20:43
@chiral-carbon
Copy link
Contributor Author

@a-r-r-o-w hi! Is this and the PR #7613 good to be merged?

Copy link
Contributor

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

@github-actions github-actions bot added the stale Issues that haven't received updates label Nov 25, 2024
@sayakpaul
Copy link
Member

@linoytsaban a gentle ping here

@github-actions github-actions bot removed the stale Issues that haven't received updates label Nov 26, 2024
Copy link
Contributor

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

@github-actions github-actions bot added the stale Issues that haven't received updates label Dec 20, 2024
@chiral-carbon
Copy link
Contributor Author

@sayakpaul @a-r-r-o-w @linoytsaban should I close this PR unless it is good to be merged? has been stale for a while

@a-r-r-o-w
Copy link
Member

Sorry for the delay. I'm triggering the tests again to make sure they pass and will merge once they do

@a-r-r-o-w a-r-r-o-w merged commit d9023a6 into huggingface:main Apr 3, 2025
7 of 9 checks passed
jonluca added a commit to weights-ai/diffusers that referenced this pull request Apr 3, 2025
* Raise warning and round down if Wan num_frames is not 4k + 1 (huggingface#11167)

* update

* raise warning and round to nearest multiple of scale factor

* [Docs] Fix environment variables in `installation.md` (huggingface#11179)

* Add `latents_mean` and `latents_std` to `SDXLLongPromptWeightingPipeline` (huggingface#11034)

* Bug fix in LTXImageToVideoPipeline.prepare_latents() when latents is already set (huggingface#10918)

* Bug fix in ltx

* Assume packed latents.

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* [tests] no hard-coded cuda  (huggingface#11186)

no cuda only

* [WIP] Add Wan Video2Video (huggingface#11053)

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* map BACKEND_RESET_MAX_MEMORY_ALLOCATED to reset_peak_memory_stats on XPU (huggingface#11191)

Signed-off-by: YAO Matrix <matrix.yao@intel.com>

* fix autocast (huggingface#11190)

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

* fix: for checking mandatory and optional pipeline components (huggingface#11189)

fix: optional componentes verification on load

* remove unnecessary call to `F.pad` (huggingface#10620)

* rewrite memory count without implicitly using dimensions by @ic-synth

* replace F.pad by built-in padding in Conv3D

* in-place sums to reduce memory allocations

* fixed trailing whitespace

* file reformatted

* in-place sums

* simpler in-place expressions

* removed in-place sum, may affect backward propagation logic

* removed in-place sum, may affect backward propagation logic

* removed in-place sum, may affect backward propagation logic

* reverted change

* allow models to run with a user-provided dtype map instead of a single dtype (huggingface#10301)

* allow models to run with a user-provided dtype map instead of a single dtype

* make style

* Add warning, change `_` to `default`

* make style

* add test

* handle shared tensors

* remove warning

---------

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

* [tests] HunyuanDiTControlNetPipeline inference precision issue on XPU (huggingface#11197)

* add xpu part

* fix more cases

* remove some cases

* no canny

* format fix

* Revert `save_model` in ModelMixin save_pretrained and use safe_serialization=False in test (huggingface#11196)

* [docs] `torch_dtype` map (huggingface#11194)

* Fix enable_sequential_cpu_offload in CogView4Pipeline (huggingface#11195)

* Fix enable_sequential_cpu_offload in CogView4Pipeline

* make fix-copies

* SchedulerMixin from_pretrained and ConfigMixin Self type annotation (huggingface#11192)

* Update import_utils.py (huggingface#10329)

added onnxruntime-vitisai for custom build onnxruntime pkg

* Add CacheMixin to Wan and LTX Transformers (huggingface#11187)

* update

* update

* update

* feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline (huggingface#11188)

* feat: [Community Pipeline] - FaithDiff Stable Diffusion XL Pipeline for Image SR.

* added pipeline

* [Model Card] standardize advanced diffusion training sdxl lora (huggingface#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>

* Change KolorsPipeline LoRA Loader to StableDiffusion (huggingface#11198)

Change LoRA Loader to StableDiffusion

Replace the SDXL LoRA Loader Mixin inheritance with the StableDiffusion one

* Update Style Bot workflow (huggingface#11202)

update style bot workflow

---------

Signed-off-by: YAO Matrix <matrix.yao@intel.com>
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: Mark <remarkablemark@users.noreply.github.com>
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: kakukakujirori <63725741+kakukakujirori@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Fanli Lin <fanli.lin@intel.com>
Co-authored-by: Yao Matrix <matrix.yao@intel.com>
Co-authored-by: jiqing-feng <jiqing.feng@intel.com>
Co-authored-by: Eliseu Silva <elismasilva@gmail.com>
Co-authored-by: Bruno Magalhaes <bruno.magalhaes@synthesia.io>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: lakshay sharma <31830611+Lakshaysharma048@users.noreply.github.com>
Co-authored-by: Abhipsha Das <ad6489@nyu.edu>
Co-authored-by: Basile Lewandowski <basile.lewan@gmail.com>
Co-authored-by: célina <hanouticelina@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
stale Issues that haven't received updates
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Tracker] use the new model card utilities for saving model cards from the training script
6 participants