Skip to content
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

Merge changes #169

Merged
merged 55 commits into from
Jul 27, 2024
Merged

Merge changes #169

merged 55 commits into from
Jul 27, 2024

Conversation

Skquark
Copy link
Owner

@Skquark Skquark commented Jul 27, 2024

No description provided.

a-r-r-o-w and others added 30 commits July 12, 2024 17:41
* fix typo in pag tests

* fix typo
include python3.10 dev and solve header missing problem
…DPM Single Step (#8269)

* Add the SDE variant of DPM-Solver and DPM-Solver++ to DPM Single Step


---------

Co-authored-by: cmdr2 <[email protected]>
fix: shard loading and saving when variant is provided.
* allow auraflow latest to be torch compile compatible.

* default to 1024 1024.
* Add AuraFlowPipeline and KolorsPipeline to auto map

Just T2I. Validated using `quickdif`

* Add Kolors I2I and SD3 Inpaint auto maps

* style

---------

Co-authored-by: yiyixuxu <[email protected]>
* Fix multi-gpu case

* Prefer previously created `unwrap_model()` function

For `torch.compile()` generalizability

* `chore: update unwrap_model() function to use accelerator.unwrap_model()`
* add pipeline docs for latte

* add inference time to latte docs

* apply review suggestions
add disable forward chunking to SD3 transformer.
* remove resume_download

* fix: _fetch_index_file call.

* remove resume_download from docs.
* initial commit

* apply suggestion to sdxl pipelines

* apply fix to sd pipelines
* fix loop bug in SlicedAttnProcessor


---------

Co-authored-by: neoshang <[email protected]>
…embedding. (#8890)

* 2d rotary pos emb dim

* make style

---------

Co-authored-by: haofanwang <[email protected]>
Mention model_info.id instead of model_info.modelId
* SD3 training fixes

Co-authored-by: bghira <[email protected]>

* rewrite noise addition part to respect the eqn.

* styler

* Update examples/dreambooth/README_sd3.md

Co-authored-by: Kashif Rasul <[email protected]>

---------

Co-authored-by: bghira <[email protected]>
Co-authored-by: Kashif Rasul <[email protected]>
* remove unused docs

* add ko-18n docs

* docs typo, edit etc

* reorder list, add `in translation` in toctree

* fix minor translation

* fix docs minor tone, etc
small fixes to pag guide.
proper skipping of request caching test
* Add attentionless VAE support

* make style and quality, fix-copies

---------

Co-authored-by: Sayak Paul <[email protected]>
* check if runner helps.

* remove caching

* gpus

* update runner group
* chore: initial model size reduction

* chore: fixing expected values for failing tests

* requested edits

---------

Co-authored-by: Sayak Paul <[email protected]>
…nsformer (#8932)

* add test for temporal transformer

* remove unused variable

* fix code quality

---------

Co-authored-by: Sayak Paul <[email protected]>
tolgacangoz and others added 25 commits July 23, 2024 18:04
* chore: Update is_google_colab check to use environment variable

* Check Colab with all possible COLAB_* env variables

* Remove unnecessary word

* Make `_is_google_colab` more inclusive

* Revert "Make `_is_google_colab` more inclusive"

This reverts commit 6406db2.

* Make `_is_google_colab` more inclusive.

* chore: Update import_utils.py with notebook check improvement

* Refactor import_utils.py to improve notebook detection for VS Code's notebook

* chore: Remove `is_notebook()` function and related code

---------

Co-authored-by: Sayak Paul <[email protected]>
* start debugging the problem,

* start

* fix

* fix

* fix imports.

* handle hunyuan

* remove residuals.

* add a check for making sure there's appropriate procs.

* add more rigor to the tests.

* fix test

* remove redundant check

* fix-copies

* move check_qkv_fusion_matches_attn_procs_length and check_qkv_fusion_processors_exist.
* remove residual i.

* rename to aura_flow in pipeline test
added line allowing gradient accumulation to work for basic_training example
* check for assertions.

* update with correct slices.

* okay

* style

* get it ready

* update

* update

* update

---------

Co-authored-by: Dhruv Nair <[email protected]>
* update

* update

* update
* speed up animatediff tests

* fix pia test_ip_adapter_single

* fix tests/pipelines/pia/test_pia.py::PIAPipelineFastTests::test_dict_tuple_outputs_equivalent

* update

* fix ip adapter tests

* skip test_from_pipe_consistent_config tests

* fix prompt_embeds test

* update test_from_pipe_consistent_config tests

* fix expected_slice values

* remove temporal_norm_num_groups from UpBlockMotion

---------

Co-authored-by: Sayak Paul <[email protected]>
Co-authored-by: Dhruv Nair <[email protected]>
* introduce  to promote reusability.

* up

* add more tests

* up

* remove comments.

* fix fuse_nan test

* clarify the scope of fuse_lora and unfuse_lora

* remove space

* rewrite fuse_lora a bit.

* feedback

* copy over load_lora_into_text_encoder.

* address dhruv's feedback.

* fix-copies

* fix issubclass.

* num_fused_loras

* fix

* fix

* remove mapping

* up

* fix

* style

* fix-copies

* change to SD3TransformerLoRALoadersMixin

* Apply suggestions from code review

Co-authored-by: Dhruv Nair <[email protected]>

* up

* handle wuerstchen

* up

* move lora to lora_pipeline.py

* up

* fix-copies

* fix documentation.

* comment set_adapters().

* fix-copies

* fix set_adapters() at the model level.

* fix?

* fix

---------

Co-authored-by: Dhruv Nair <[email protected]>
* Update TensorRT img2img pipeline

Signed-off-by: Asfiya Baig <[email protected]>

* Update TensorRT version installed

Signed-off-by: Asfiya Baig <[email protected]>

* make style and quality

Signed-off-by: Asfiya Baig <[email protected]>

* Update examples/community/stable_diffusion_tensorrt_img2img.py

Co-authored-by: Tolga Cangöz <[email protected]>

* Update examples/community/README.md

Co-authored-by: Tolga Cangöz <[email protected]>

* Apply style and quality using ruff 0.1.5

Signed-off-by: Asfiya Baig <[email protected]>

---------

Signed-off-by: Asfiya Baig <[email protected]>
Co-authored-by: Tolga Cangöz <[email protected]>
Co-authored-by: Dhruv Nair <[email protected]>
modify in_channels in network_config params

Co-authored-by: Dhruv Nair <[email protected]>
Revert "[LoRA] introduce LoraBaseMixin to promote reusability. (#8774)"

This reverts commit 527430d.
fix guidance_scale value not equal with the value in comments
remove all is from auraflow.
* introduce  to promote reusability.

* up

* add more tests

* up

* remove comments.

* fix fuse_nan test

* clarify the scope of fuse_lora and unfuse_lora

* remove space

* rewrite fuse_lora a bit.

* feedback

* copy over load_lora_into_text_encoder.

* address dhruv's feedback.

* fix-copies

* fix issubclass.

* num_fused_loras

* fix

* fix

* remove mapping

* up

* fix

* style

* fix-copies

* change to SD3TransformerLoRALoadersMixin

* Apply suggestions from code review

Co-authored-by: Dhruv Nair <[email protected]>

* up

* handle wuerstchen

* up

* move lora to lora_pipeline.py

* up

* fix-copies

* fix documentation.

* comment set_adapters().

* fix-copies

* fix set_adapters() at the model level.

* fix?

* fix

* loraloadermixin.

---------

Co-authored-by: Dhruv Nair <[email protected]>
)

added accelerator based gradient accumulation for basic_example

Co-authored-by: Sayak Paul <[email protected]>
* fix step index out of bounds

* add test for free_init with different schedulers

* add test to vid2vid and pia
* initial sparse control model draft

* remove unnecessary implementation

* copy animatediff pipeline

* remove deprecated callbacks

* update

* update pipeline implementation progress

* make style

* make fix-copies

* update progress

* add partially working pipeline

* remove debug prints

* add model docs

* dummy objects

* improve motion lora conversion script

* fix bugs

* update docstrings

* remove unnecessary model params; docs

* address review comment

* add copied from to zero_module

* copy animatediff test

* add fast tests

* update docs

* update

* update pipeline docs

* fix expected slice values

* fix license

* remove get_down_block usage

* remove temporal_double_self_attention from get_down_block

* update

* update docs with org and documentation images

* make from_unet work in sparsecontrolnetmodel

* add latest freeinit test from #8969

* make fix-copies

* LoraLoaderMixin -> StableDiffsuionLoraLoaderMixin
* initial draft

* apply suggestions

* fix failing test

* added ipa to img2img

* add docs

* apply suggestions
@Skquark Skquark merged commit 5fc0ad3 into Skquark:main Jul 27, 2024
8 of 11 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.