hlky
ca6330dc53
Fix use_lu_lambdas and use_karras_sigmas with beta_schedule=squaredcos_cap_v2 in DPMSolverMultistepScheduler ( #10740 )
2025-02-12 20:33:56 +00:00
Dhruv Nair
28f48f4051
[Single File] Add Single File support for Lumina Image 2.0 Transformer ( #10781 )
...
* update
* update
2025-02-12 18:53:49 +05:30
Thanh Le
067eab1b3a
Faster set_adapters ( #10777 )
...
* Update peft_utils.py
* Update peft_utils.py
* Update peft_utils.py
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-02-12 16:30:09 +05:30
Aryan
57ac673802
Refactor OmniGen ( #10771 )
...
* OmniGen model.py
* update OmniGenTransformerModel
* omnigen pipeline
* omnigen pipeline
* update omnigen_pipeline
* test case for omnigen
* update omnigenpipeline
* update docs
* update docs
* offload_transformer
* enable_transformer_block_cpu_offload
* update docs
* reformat
* reformat
* reformat
* update docs
* update docs
* make style
* make style
* Update docs/source/en/api/models/omnigen_transformer.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* update docs
* revert changes to examples/
* update OmniGen2DModel
* make style
* update test cases
* Update docs/source/en/api/pipelines/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* update docs
* typo
* Update src/diffusers/models/embeddings.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/attention.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/transformers/transformer_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/transformers/transformer_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/transformers/transformer_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update tests/pipelines/omnigen/test_pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update tests/pipelines/omnigen/test_pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* consistent attention processor
* updata
* update
* check_inputs
* make style
* update testpipeline
* update testpipeline
* refactor omnigen
* more updates
* apply review suggestion
---------
Co-authored-by: shitao <2906698981@qq.com >
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
Co-authored-by: hlky <hlky@hlky.ac >
2025-02-12 14:06:14 +05:30
Le Zhuo
81440fd474
Add support for lumina2 ( #10642 )
...
* Add support for lumina2
---------
Co-authored-by: csuhan <hanjiaming@whu.edu.cn >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: Aryan <aryan@huggingface.co >
Co-authored-by: hlky <hlky@hlky.ac >
2025-02-11 11:38:33 -10:00
Eliseu Silva
c470274865
feat: new community mixture_tiling_sdxl pipeline for SDXL ( #10759 )
...
* feat: new community mixture_tiling_sdxl pipeline for SDXL mixture-of-diffusers support
* fix use of variable latents to tile_latents
* removed references to modules that are not being used in this pipeline
* make style, make quality
2025-02-11 18:01:42 -03:00
Shitao Xiao
798e17187d
Add OmniGen ( #10148 )
...
* OmniGen model.py
* update OmniGenTransformerModel
* omnigen pipeline
* omnigen pipeline
* update omnigen_pipeline
* test case for omnigen
* update omnigenpipeline
* update docs
* update docs
* offload_transformer
* enable_transformer_block_cpu_offload
* update docs
* reformat
* reformat
* reformat
* update docs
* update docs
* make style
* make style
* Update docs/source/en/api/models/omnigen_transformer.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* update docs
* revert changes to examples/
* update OmniGen2DModel
* make style
* update test cases
* Update docs/source/en/api/pipelines/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/using-diffusers/omnigen.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* update docs
* typo
* Update src/diffusers/models/embeddings.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/attention.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/transformers/transformer_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/transformers/transformer_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/models/transformers/transformer_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update tests/pipelines/omnigen/test_pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update tests/pipelines/omnigen/test_pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/omnigen/pipeline_omnigen.py
Co-authored-by: hlky <hlky@hlky.ac >
* consistent attention processor
* updata
* update
* check_inputs
* make style
* update testpipeline
* update testpipeline
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
Co-authored-by: hlky <hlky@hlky.ac >
Co-authored-by: Aryan <aryan@huggingface.co >
2025-02-12 02:16:38 +05:30
Dhruv Nair
ed4b75229f
[CI] Fix Truffle Hog failure ( #10769 )
...
* update
* update
2025-02-11 22:41:03 +05:30
Mathias Parger
8ae8008b0d
speedup hunyuan encoder causal mask generation ( #10764 )
...
* speedup causal mask generation
* fixing hunyuan attn mask test case
2025-02-11 16:03:15 +05:30
Sayak Paul
c80eda9d3e
[Tests] Test layerwise casting with training ( #10765 )
...
* add a test to check if we can train with layerwise casting.
* updates
* updates
* style
2025-02-11 16:02:28 +05:30
hlky
7fb481f840
Add Self type hint to ModelMixin's from_pretrained ( #10742 )
2025-02-10 09:17:57 -10:00
Sayak Paul
9f5ad1db41
[LoRA] fix peft state dict parsing ( #10532 )
...
* fix peft state dict parsing
* updates
2025-02-10 18:47:20 +05:30
hlky
464374fb87
EDMEulerScheduler accept sigmas, add final_sigmas_type ( #10734 )
2025-02-07 06:53:52 +00:00
hlky
d43ce14e2d
Quantized Flux with IP-Adapter ( #10728 )
2025-02-06 07:02:36 -10:00
Leo Jiang
cd0a4a82cf
[bugfix] NPU Adaption for Sana ( #10724 )
...
* 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 >
2025-02-06 19:29:58 +05:30
suzukimain
145522cbb7
[Community] Enhanced Model Search ( #10417 )
...
* Added `auto_load_textual_inversion` and `auto_load_lora_weights`
* update README.md
* fix
* make quality
* Fix and `make style`
2025-02-05 14:43:53 -10:00
xieofxie
23bc56a02d
add provider_options in from_pretrained ( #10719 )
...
Co-authored-by: hualxie <hualxie@microsoft.com >
2025-02-05 09:41:41 -10:00
SahilCarterr
5b1dcd1584
[Fix] Type Hint in from_pretrained() to Ensure Correct Type Inference ( #10714 )
...
* Update pipeline_utils.py
Added Self in from_pretrained method so inference will correctly recognize pipeline
* Use typing_extensions
---------
Co-authored-by: hlky <hlky@hlky.ac >
2025-02-04 08:59:31 -10:00
Parag Ekbote
dbe0094e86
Notebooks for Community Scripts-6 ( #10713 )
...
* Fix Doc Tutorial.
* Add 4 Notebooks and improve their example
scripts.
2025-02-04 10:12:17 -08:00
Nicolas
f63d32233f
Fix train_text_to_image.py --help ( #10711 )
2025-02-04 11:26:23 +05:30
Sayak Paul
5e8e6cb44f
[bitsandbytes] Simplify bnb int8 dequant ( #10401 )
...
* fix dequantization for latest bnb.
* smol fixes.
* fix type annotation
* update peft link
* updates
2025-02-04 11:17:14 +05:30
Parag Ekbote
3e35f56b00
Fix Documentation about Image-to-Image Pipeline ( #10704 )
...
Fix Doc Tutorial.
2025-02-03 09:54:00 -08:00
Ikpreet S Babra
537891e693
Fixed grammar in "write_own_pipeline" readme ( #10706 )
2025-02-03 09:53:30 -08:00
Vedat Baday
9f28f1abba
feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling ( #10699 )
...
* feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling
* chore: update type hint
* refactor: use union for type hint
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-02-01 23:04:05 +05:30
Thanh Le
5d2d23986e
Fix inconsistent random transform in instruct pix2pix ( #10698 )
...
* Update train_instruct_pix2pix.py
Fix inconsistent random transform in instruct_pix2pix
* Update train_instruct_pix2pix_sdxl.py
2025-01-31 08:29:29 -10:00
Max Podkorytov
1ae9b0595f
Fix enable memory efficient attention on ROCm ( #10564 )
...
* fix enable memory efficient attention on ROCm
while calling CK implementation
* Update attention_processor.py
refactor of picking a set element
2025-01-31 17:15:49 +05:30
SahilCarterr
aad69ac2f3
[FIX] check_inputs function in Auraflow Pipeline ( #10678 )
...
fix_shape_error
2025-01-29 13:11:54 -10:00
Vedat Baday
ea76880bd7
fix(hunyuan-video): typo in height and width input check ( #10684 )
2025-01-30 04:16:05 +05:30
Teriks
33f936154d
support StableDiffusionAdapterPipeline.from_single_file ( #10552 )
...
* support StableDiffusionAdapterPipeline.from_single_file
* make style
---------
Co-authored-by: Teriks <Teriks@users.noreply.github.com >
Co-authored-by: hlky <hlky@hlky.ac >
2025-01-29 07:18:47 -10:00
Sayak Paul
e6037e8275
[tests] update llamatokenizer in hunyuanvideo tests ( #10681 )
...
update llamatokenizer in hunyuanvideo tests
2025-01-29 21:12:57 +05:30
Dimitri Barbot
196aef5a6f
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
2025-01-28 10:46:41 -03:00
Sayak Paul
7b100ce589
[Tests] conditionally check fp8_e4m3_bf16_max_memory < fp8_e4m3_fp32_max_memory ( #10669 )
...
* conditionally check if compute capability is met.
* log info.
* fix condition.
* updates
* updates
* updates
* updates
2025-01-28 12:00:14 +05:30
Aryan
c4d4ac21e7
Refactor gradient checkpointing ( #10611 )
...
* update
* remove unused fn
* apply suggestions based on review
* update + cleanup 🧹
* more cleanup 🧹
* make fix-copies
* update test
2025-01-28 06:51:46 +05:30
Hanch Han
f295e2eefc
[fix] refer use_framewise_encoding on AutoencoderKLHunyuanVideo._encode ( #10600 )
...
* fix: refer to use_framewise_encoding on AutoencoderKLHunyuanVideo._encode
* fix: comment about tile_sample_min_num_frames
---------
Co-authored-by: Aryan <aryan@huggingface.co >
2025-01-28 06:51:27 +05:30
Aryan
658e24e86c
[core] Pyramid Attention Broadcast ( #9562 )
...
* start pyramid attention broadcast
* add coauthor
Co-Authored-By: Xuanlei Zhao <43881818+oahzxl@users.noreply.github.com >
* update
* make style
* update
* make style
* add docs
* add tests
* update
* Update docs/source/en/api/pipelines/cogvideox.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Update docs/source/en/api/pipelines/cogvideox.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* Pyramid Attention Broadcast rewrite + introduce hooks (#9826 )
* rewrite implementation with hooks
* make style
* update
* merge pyramid-attention-rewrite-2
* make style
* remove changes from latte transformer
* revert docs changes
* better debug message
* add todos for future
* update tests
* make style
* cleanup
* fix
* improve log message; fix latte test
* refactor
* update
* update
* update
* revert changes to tests
* update docs
* update tests
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* update
* fix flux test
* reorder
* refactor
* make fix-copies
* update docs
* fixes
* more fixes
* make style
* update tests
* update code example
* make fix-copies
* refactor based on reviews
* use maybe_free_model_hooks
* CacheMixin
* make style
* update
* add current_timestep property; update docs
* make fix-copies
* update
* improve tests
* try circular import fix
* apply suggestions from review
* address review comments
* Apply suggestions from code review
* refactor hook implementation
* add test suite for hooks
* PAB Refactor (#10667 )
* update
* update
* update
---------
Co-authored-by: DN6 <dhruv.nair@gmail.com >
* update
* fix remove hook behaviour
---------
Co-authored-by: Xuanlei Zhao <43881818+oahzxl@users.noreply.github.com >
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
Co-authored-by: DN6 <dhruv.nair@gmail.com >
2025-01-28 05:09:04 +05:30
Giuseppe Catalano
fb42066489
Revert RePaint scheduler 'fix' ( #10644 )
...
Co-authored-by: Giuseppe Catalano <giuseppelorenzo.catalano@unito.it >
2025-01-27 11:16:45 -10:00
Teriks
e89ab5bc26
SDXL ControlNet Union pipelines, make control_image argument immutible ( #10663 )
...
controlnet union XL, make control_image immutible
when this argument is passed a list, __call__
modifies its content, since it is pass by reference
the list passed by the caller gets its content
modified unexpectedly
make a copy at method intro so this does not happen
Co-authored-by: Teriks <Teriks@users.noreply.github.com >
2025-01-27 10:53:30 -10:00
victolee0
8ceec90d76
fix check_inputs func in LuminaText2ImgPipeline ( #10651 )
2025-01-27 09:47:01 -10:00
hlky
158c5c4d08
Add provider_options to OnnxRuntimeModel ( #10661 )
2025-01-27 09:46:17 -10:00
hlky
41571773d9
[training] Convert to ImageFolder script ( #10664 )
...
* [training] Convert to ImageFolder script
* make
2025-01-27 09:43:51 -10:00
hlky
18f7d1d937
ControlNet Union controlnet_conditioning_scale for multiple control inputs ( #10666 )
2025-01-27 08:15:25 -10:00
Marlon May
f7f36c7d3d
Add community pipeline for semantic guidance for FLUX ( #10610 )
...
* 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 >
2025-01-27 16:19:46 +02:00
Yuqian Hong
4fa24591a3
create a script to train autoencoderkl ( #10605 )
...
* 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 >
2025-01-27 16:41:34 +05:30
Jacob Helwig
4f3ec5364e
Add sigmoid scheduler in scheduling_ddpm.py docs ( #10648 )
...
Sigmoid scheduler in scheduling_ddpm.py docs
2025-01-26 15:37:20 -08:00
Leo Jiang
07860f9916
NPU Adaption for Sanna ( #10409 )
...
* NPU Adaption for Sanna
---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-01-24 09:08:52 -10:00
Wenhao Sun
87252d80c3
Add pipeline_stable_diffusion_xl_attentive_eraser ( #10579 )
...
* 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 >
2025-01-24 13:52:45 +00:00
Sayak Paul
5897137397
[chore] add a script to extract loras from full fine-tuned models ( #10631 )
...
* feat: add a lora extraction script.
* updates
2025-01-24 11:50:36 +05:30
Yaniv Galron
a451c0ed14
removing redundant requires_grad = False ( #10628 )
...
We already set the unet to requires grad false at line 506
Co-authored-by: Aryan <aryan@huggingface.co >
2025-01-24 03:25:33 +05:30
hlky
37c9697f5b
Add IP-Adapter example to Flux docs ( #10633 )
...
* Add IP-Adapter example to Flux docs
* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-01-23 22:15:33 +05:30
Raul Ciotescu
9684c52adf
width and height are mixed-up ( #10629 )
...
vars mixed-up
2025-01-23 06:40:22 -10:00
