Anatoly Belikov
f240a936da
handle lora scale and clip skip in lpw sd and sdxl community pipelines ( #8988 )
...
* handle lora scale and clip skip in lpw sd and sdxl
* use StableDiffusionLoraLoaderMixin
* use StableDiffusionXLLoraLoaderMixin
* style
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-07-30 07:19:28 +05:30
Sayak Paul
00d8d46e23
[Docs] credit where it's due for Lumina and Latte. ( #9000 )
...
credit where it's due for Lumina and Latte.
2024-07-29 10:02:03 -07:00
Adrien
bfc9369f0a
[CI] Update runner configuration for setup and nightly tests ( #9005 )
...
* [CI] Update runner configuration for setup and nightly tests
Signed-off-by: Adrien <adrien@huggingface.co >
* fix group
Signed-off-by: Adrien <adrien@huggingface.co >
* update for t4
Signed-off-by: Adrien <adrien@huggingface.co >
---------
Signed-off-by: Adrien <adrien@huggingface.co >
2024-07-29 21:14:31 +05:30
Γlvaro Somoza
73acebb8cf
[Kolors] Add IP Adapter ( #8901 )
...
* initial draft
* apply suggestions
* fix failing test
* added ipa to img2img
* add docs
* apply suggestions
2024-07-26 14:25:44 -04:00
Aryan
ca0747a07e
remove unused code from pag attn procs ( #8928 )
2024-07-26 07:58:40 -10:00
Aryan
5c53ca5ed8
[core] AnimateDiff SparseCtrl ( #8897 )
...
* 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
2024-07-26 17:46:05 +05:30
Aryan
57a021d5e4
[fix] FreeInit step index out of bounds ( #8969 )
...
* fix step index out of bounds
* add test for free_init with different schedulers
* add test to vid2vid and pia
2024-07-26 16:45:55 +05:30
Dhruv Nair
1168eaaadd
[CI] Nightly Test Runner explicitly set runner for Setup Pipeline Matrix ( #8986 )
...
* update
* update
* update
2024-07-26 13:20:35 +05:30
Dhruv Nair
bce9105ac7
[CI] Fix parallelism in nightly tests ( #8983 )
...
update
2024-07-26 10:04:01 +05:30
RandomGamingDev
2afb2e0aac
Added accelerator based gradient accumulation for basic_example ( #8966 )
...
added accelerator based gradient accumulation for basic_example
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-07-26 09:35:52 +05:30
Sayak Paul
d87fe95f90
[Chore] add LoraLoaderMixin to the inits ( #8981 )
...
* 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 <dhruv.nair@gmail.com >
* 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 <dhruv.nair@gmail.com >
2024-07-26 08:59:33 +05:30
Sayak Paul
50e66f2f95
[Chore] remove all is from auraflow. ( #8980 )
...
remove all is from auraflow.
2024-07-26 07:31:06 +05:30
efwfe
9b8c8605d1
fix guidance_scale value not equal to the value in comments ( #8941 )
...
fix guidance_scale value not equal with the value in comments
2024-07-25 12:31:37 -10:00
YiYi Xu
62863bb1ea
Revert "[LoRA] introduce LoraBaseMixin to promote reusability." ( #8976 )
...
Revert "[LoRA] introduce LoraBaseMixin to promote reusability. (#8774 )"
This reverts commit 527430d0a4
2024-07-25 09:10:35 -10:00
mazharosama
1fd647f2a0
Enable CivitAI SDXL Inpainting Models Conversion ( #8795 )
...
modify in_channels in network_config params
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-07-25 07:44:57 -10:00
asfiyab-nvidia
0bda1d7b89
Update TensorRT img2img community pipeline ( #8899 )
...
* Update TensorRT img2img pipeline
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com >
* Update TensorRT version installed
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com >
* make style and quality
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com >
* Update examples/community/stable_diffusion_tensorrt_img2img.py
Co-authored-by: Tolga CangΓΆz <46008593+tolgacangoz@users.noreply.github.com >
* Update examples/community/README.md
Co-authored-by: Tolga CangΓΆz <46008593+tolgacangoz@users.noreply.github.com >
* Apply style and quality using ruff 0.1.5
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com >
---------
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com >
Co-authored-by: Tolga CangΓΆz <46008593+tolgacangoz@users.noreply.github.com >
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-07-25 21:58:21 +05:30
Sayak Paul
527430d0a4
[LoRA] introduce LoraBaseMixin to promote reusability. ( #8774 )
...
* 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 <dhruv.nair@gmail.com >
* 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 <dhruv.nair@gmail.com >
2024-07-25 21:40:58 +05:30
Aryan
3ae0ee88d3
[tests] speed up animatediff tests ( #8846 )
...
* 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 <spsayakpaul@gmail.com >
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-07-25 17:35:43 +05:30
Dhruv Nair
5fbb4d32d5
[CI] Slow Test Updates ( #8870 )
...
* update
* update
* update
2024-07-25 16:00:43 +05:30
Sayak Paul
d8bcb33f4b
[Tests] fix slices of 26 tests (first half) ( #8959 )
...
* check for assertions.
* update with correct slices.
* okay
* style
* get it ready
* update
* update
* update
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-07-25 14:56:49 +05:30
Sanchit Gandhi
4a782f462a
[AudioLDM2] Fix cache pos for GPT-2 generation ( #8964 )
...
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-07-25 09:21:49 +05:30
RandomGamingDev
cdd12bde17
Added Code for Gradient Accumulation to work for basic_training ( #8961 )
...
added line allowing gradient accumulation to work for basic_training example
2024-07-25 08:40:53 +05:30
Sayak Paul
2c25b98c8e
[AuraFlow] fix long prompt handling ( #8937 )
...
fix
2024-07-24 11:19:30 +05:30
Dhruv Nair
93983b6780
[CI] Skip flaky download tests in PR CI ( #8945 )
...
update
2024-07-24 09:25:06 +05:30
Sayak Paul
41b705f42d
remove residual i from auraflow. ( #8949 )
...
* remove residual i.
* rename to aura_flow in pipeline test
2024-07-24 07:31:54 +05:30
Sayak Paul
50d21f7c6a
[Core] fix QKV fusion for attention ( #8829 )
...
* 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.
2024-07-24 06:52:19 +05:30
Dhruv Nair
3bb1fd6fc0
Fix name when saving text inversion embeddings in dreambooth advanced scripts ( #8927 )
...
update
2024-07-23 19:51:20 +05:30
Tolga CangΓΆz
cf55dcf0ff
Fix Colab and Notebook checks for diffusers-cli env ( #8408 )
...
* 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 6406db21acspsayakpaul@gmail.com >
2024-07-23 18:04:20 +05:30
Vinh H. Pham
7a95f8d9d8
[Tests] Improve transformers model test suite coverage - Temporal Transformer ( #8932 )
...
* add test for temporal transformer
* remove unused variable
* fix code quality
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-07-23 15:36:30 +05:30
akbaig
7710415baf
fix: checkpoint save issue in advanced dreambooth lora sdxl script ( #8926 )
...
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com >
2024-07-23 14:44:56 +05:30
Aritra Roy Gosthipaty
8b21feed42
[Tests] reduce the model size in the audioldm2 fast test ( #7846 )
...
* chore: initial model size reduction
* chore: fixing expected values for failing tests
* requested edits
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-07-23 14:34:07 +05:30
Dhruv Nair
f57b27d2ad
Update pipeline test fetcher ( #8931 )
...
update
2024-07-23 10:02:22 +05:30
Sayak Paul
c5fdf33a10
[Benchmarking] check if runner helps to restore benchmarking ( #8929 )
...
* check if runner helps.
* remove caching
* gpus
* update runner group
2024-07-23 06:38:13 +05:30
Vishnu V Jaddipal
77c5de2e05
Add attentionless VAE support ( #8769 )
...
* Add attentionless VAE support
* make style and quality, fix-copies
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-07-22 14:16:58 -10:00
Sayak Paul
af400040f5
[Tests] proper skipping of request caching test ( #8908 )
...
proper skipping of request caching test
2024-07-22 12:52:57 -10:00
Jiwook Han
5802c2e3f2
Reflect few contributions on ethical_guidelines.md that were not reflected on #8294 ( #8914 )
...
fix_ethical_guidelines.md
2024-07-22 08:48:23 -07:00
Sayak Paul
f4af03b350
[Docs] small fixes to pag guide. ( #8920 )
...
small fixes to pag guide.
2024-07-22 08:35:01 -07:00
Seongsu Park
267bf65707
π [i18n-KO] Translated docs to Korean (added 7 docs and etc) ( #8804 )
...
* 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
2024-07-22 08:08:44 -07:00
Sayak Paul
1a8b3c2ee8
[Training] SD3 training fixes ( #8917 )
...
* SD3 training fixes
Co-authored-by: bghira <59658056+bghira@users.noreply.github.com >
* rewrite noise addition part to respect the eqn.
* styler
* Update examples/dreambooth/README_sd3.md
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com >
---------
Co-authored-by: bghira <59658056+bghira@users.noreply.github.com >
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com >
2024-07-21 16:24:04 +05:30
Lucain
56e772ab7e
Use model_info.id instead of model_info.modelId ( #8912 )
...
Mention model_info.id instead of model_info.modelId
2024-07-20 20:01:21 +05:30
Pierre Chapuis
fe7948941d
allow tensors in several schedulers step() call ( #8905 )
2024-07-19 18:58:06 -10:00
ηε₯ε
461efc57c5
[fix code annotation] Adjust the dimensions of the rotary positional embedding. ( #8890 )
...
* 2d rotary pos emb dim
* make style
---------
Co-authored-by: haofanwang <haofanwang.ai@gmail.com >
2024-07-19 18:57:36 -10:00
shinetzh
3b04cdc816
fix loop bug in SlicedAttnProcessor ( #8836 )
...
* fix loop bug in SlicedAttnProcessor
---------
Co-authored-by: neoshang <neoshang@tencent.com >
2024-07-19 18:14:29 -10:00
Γlvaro Somoza
c009c203be
[SDXL] Fix uncaught error with image to image ( #8856 )
...
* initial commit
* apply suggestion to sdxl pipelines
* apply fix to sd pipelines
2024-07-19 12:06:36 -10:00
Dhruv Nair
3f1411767b
SSH into cpu runner additional fix ( #8893 )
...
* update
* update
* update
2024-07-18 16:18:45 +05:30
Dhruv Nair
588fb5c105
SSH into cpu runner fix ( #8888 )
...
* update
* update
2024-07-18 11:00:05 +05:30
Dhruv Nair
eb24e4bdb2
Add option to SSH into CPU runner. ( #8884 )
...
update
2024-07-18 10:20:24 +05:30
Sayak Paul
e02ec27e51
[Core] remove resume_download from Hub related stuff ( #8648 )
...
* remove resume_download
* fix: _fetch_index_file call.
* remove resume_download from docs.
2024-07-18 09:48:42 +05:30
Sayak Paul
a41e4c506b
[Chore] add disable forward chunking to SD3 transformer. ( #8838 )
...
add disable forward chunking to SD3 transformer.
2024-07-18 09:30:18 +05:30
Aryan
12625c1c9c
[docs] pipeline docs for latte ( #8844 )
...
* add pipeline docs for latte
* add inference time to latte docs
* apply review suggestions
2024-07-18 09:27:48 +05:30
