yiyixuxu
d34c4e8caf
update the description of StableDiffusionXLDenoiseLoopWrapper
2025-06-20 07:38:21 +02:00
yiyixuxu
b46b7c8b31
add to method to modular loader, copied from DiffusionPipeline, not tested yet
2025-06-20 07:25:20 +02:00
yiyixuxu
fc9168f429
add block mappings to modular_diffusers.stable_diffusion_xl.__init__
2025-06-20 07:24:14 +02:00
yiyixuxu
31a31ca1c5
rename modular_pipeline_block_mappings.py to modular_block_mapping
2025-06-20 07:23:14 +02:00
yiyixuxu
8423652b35
updatee modular_pipeline.from_pretrained, modular_repo ->pretrained_model_name_or_path
2025-06-19 05:30:18 +02:00
yiyixuxu
de631947cc
up
2025-06-19 04:45:20 +02:00
yiyixuxu
58e9565719
update doc format for kwargs_type
2025-06-19 02:24:51 +02:00
yiyixuxu
cb6d5fed19
refator based on dhruv's feedbacks
2025-06-18 10:11:22 +02:00
yiyixuxu
f16e9c7807
add
2025-06-10 23:10:17 +02:00
yiyixuxu
87f63d424a
modular node!
2025-05-22 11:50:36 +02:00
yiyixuxu
29de29f02c
add node_utils
2025-05-21 22:31:10 +02:00
yiyixuxu
72e1b74638
solve merge conflict: manually add back the remote code change to modular_pipeline
2025-05-20 20:26:51 +02:00
yiyixuxu
3471f2fb75
merge part1
2025-05-20 18:53:04 +02:00
yiyixuxu
d136ae36c8
update input for loop blocks, do not need to include intermediate
2025-05-20 18:11:05 +02:00
yiyixuxu
1b89ac144c
prepare_latents_img2img pipeline method -> function, maybe do the same for others?
2025-05-20 18:10:06 +02:00
yiyixuxu
eb9415031a
add a to-do for modular loader
2025-05-20 18:08:28 +02:00
yiyixuxu
de6ab6b49d
fix import in block mapping
2025-05-20 18:07:58 +02:00
yiyixuxu
4968edc5dc
remove the duplicated components_manager file I forgot to deletee
2025-05-20 18:07:27 +02:00
Dhruv Nair
808dff09cb
[WIP] Modular Diffusers support custom code/pipeline blocks ( #11539 )
...
* update
* update
2025-05-20 15:12:51 +05:30
yiyixuxu
61dac3bbe4
up
2025-05-19 22:39:32 +02:00
yiyixuxu
73ab5725c2
update components manager
2025-05-18 19:09:01 +02:00
yiyixuxu
163341d3dd
refactor modular loader: 1. load only load (pretrained components only if not specific names) 2. update acceept create spec 3. move the updte _componeent_spec logic outside register_components to each method that create/update the component: __init__/update/load
2025-05-18 18:58:26 +02:00
yiyixuxu
d0fbf745e6
refactor component spec: replace create/create_from_pretrained/create_from_config to just create and load method
2025-05-18 18:52:12 +02:00
yiyixuxu
27c1158b23
add a to-do for guider cconfig mixin
2025-05-18 18:50:03 +02:00
yiyixuxu
96ce6744fe
after_denoise -> decoders
2025-05-15 00:45:45 +02:00
yiyixuxu
8ad14a52cb
make generator intermediates (it is mutable)
2025-05-13 23:25:56 +02:00
yiyixuxu
a7fb2d2a22
remove the output step
2025-05-13 22:15:54 +02:00
yiyixuxu
a0deefb606
fix more
2025-05-13 20:51:21 +02:00
yiyixuxu
e2491af650
fix import
2025-05-13 20:42:57 +02:00
yiyixuxu
506a8ea09c
fix imports
2025-05-13 04:36:06 +02:00
yiyixuxu
58358c2d00
decode block, if skip decoding do not need to update latent
2025-05-13 01:57:47 +02:00
yiyixuxu
5cde77f915
make inputs truly immutable, remove the output logic in sequential pipeline, and update so that intermediates_outputs are only new variables
2025-05-13 01:52:51 +02:00
yiyixuxu
522e827625
move block mappings to its own file
2025-05-12 01:17:45 +02:00
yiyixuxu
144eae4e0b
add block state will also make sure modifed intermediates_inputs will be updated
2025-05-12 01:16:42 +02:00
yiyixuxu
796453cad1
add notes
2025-05-12 01:14:43 +02:00
yiyixuxu
153ae34ff6
update __init__
2025-05-10 03:50:47 +02:00
yiyixuxu
0acb5e1460
made a modular_pipelines folder!
2025-05-10 03:50:31 +02:00
yiyixuxu
462429b687
remove modular reelated change from pipelines folder
2025-05-10 03:50:10 +02:00
yiyixuxu
cf01aaeb49
update imports on guiders
2025-05-10 03:49:30 +02:00
yiyixuxu
2017ae5624
fix auto denoise so all tests pass
2025-05-09 08:19:24 +02:00
yiyixuxu
2b361a2413
fix get_execusion blocks with loopsequential
2025-05-09 08:17:10 +02:00
yiyixuxu
c677d528e4
change warning to debug
2025-05-09 08:16:24 +02:00
yiyixuxu
0f0618ff2b
refactor the denoiseestep using LoopSequential! also add a new file for denoise step
2025-05-08 11:28:52 +02:00
yiyixuxu
d89631fc50
update input formating, consider kwarggs_type inputs with no name, e/g *_controlnet_kwargs
2025-05-08 11:27:17 +02:00
yiyixuxu
16b6583fa8
allow input_fields as input & update message
2025-05-08 11:25:31 +02:00
yiyixuxu
f552773572
remove controlnet union denoise step, refactor & reuse controlnet denoisee step to accept aditional contrlnet kwargs
2025-05-06 10:00:14 +02:00
yiyixuxu
dc4dbfe107
reefactor pipeline/block states so that it can dynamically accept kwargs
2025-05-06 09:58:44 +02:00
yiyixuxu
43ac1ff7e7
refactor controlnet union
2025-05-04 22:17:25 +02:00
yiyixuxu
efd70b7838
seperate controlnet step into input + denoise
2025-05-03 20:22:05 +02:00
yiyixuxu
7ca860c24b
rename pipeline -> components, data -> block_state
2025-05-03 01:32:59 +02:00
yiyixuxu
7b86fcea31
remove lora step and ip-adapter step -> no longer needed
2025-05-02 11:31:25 +02:00
yiyixuxu
c8b5d56412
make loader optional
2025-05-02 00:46:31 +02:00
YiYi Xu
ce642e92da
Merge branch 'modular-diffusers' into modular-refactor
2025-04-30 17:56:51 -10:00
YiYi Xu
6a509ba862
Merge branch 'main' into modular-diffusers
2025-04-30 17:56:25 -10:00
YiYi Xu
6d5beefe29
[modular diffusers] introducing ModularLoader ( #11462 )
...
* cfg; slg; pag; sdxl without controlnet
---------
Co-authored-by: Aryan <aryan@huggingface.co >
2025-04-30 11:17:20 -10:00
Yao Matrix
06beecafc5
make autoencoders. controlnet_flux and wan_transformer3d_single_file pass on xpu ( #11461 )
...
* make autoencoders. controlnet_flux and wan_transformer3d_single_file
pass on XPU
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* Apply style fixes
---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co >
2025-05-01 02:43:31 +05:30
Vaibhav Kumawat
daf0a23958
Add LANCZOS as default interplotation mode. ( #11463 )
...
* Add LANCZOS as default interplotation mode.
* LANCZOS as default interplotation
* LANCZOS as default interplotation mode
* Added LANCZOS as default interplotation mode
2025-04-30 14:22:38 -04:00
tongyu
38ced7ee59
[test_models_transformer_hunyuan_video] help us test torch.compile() for impactful models ( #11431 )
...
* Update test_models_transformer_hunyuan_video.py
* update
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-04-30 19:11:42 +08:00
Yao Matrix
23c98025b3
make safe diffusion test cases pass on XPU and A100 ( #11458 )
...
* make safe diffusion test cases pass on XPU and A100
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* calibrate A100 expected values
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
2025-04-30 16:05:28 +05:30
captainzz
8cd7426e56
Add StableDiffusion3InstructPix2PixPipeline ( #11378 )
...
* upload StableDiffusion3InstructPix2PixPipeline
* Move to community
* Add readme
* Fix images
* remove images
* Change image url
* fix
* Apply style fixes
2025-04-30 06:13:12 -04:00
Daniel Socek
fbce7aeb32
Add generic support for Intel Gaudi accelerator (hpu device) ( #11328 )
...
* Add generic support for Intel Gaudi accelerator (hpu device)
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
Co-authored-by: Libin Tang <libin.tang@intel.com >
* Add loggers for generic HPU support
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
* Refactor hpu support with is_hpu_available() logic
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
* Fix style for hpu support update
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
* Decouple soft HPU check from hard device validation to support HPU migration
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
---------
Signed-off-by: Daniel Socek <daniel.socek@intel.com >
Co-authored-by: Libin Tang <libin.tang@intel.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-04-30 14:45:02 +05:30
Yao Matrix
35fada4169
enable unidiffuser test cases on xpu ( #11444 )
...
* enable unidiffuser cases on XPU
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix a typo
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-30 13:58:00 +05:30
Yao Matrix
fbe2fe5578
enable consistency test cases on XPU, all passed ( #11446 )
...
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-30 12:41:29 +05:30
Aryan
c86511586f
torch.compile fullgraph compatibility for Hunyuan Video (#11457 )
...
udpate
2025-04-30 11:21:17 +05:30
Yao Matrix
60892c55a4
enable marigold_intrinsics cases on XPU ( #11445 )
...
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-30 11:07:37 +05:30
Aryan
8fe5a14d9b
Raise warning instead of error for block offloading with streams ( #11425 )
...
raise warning instead of error
2025-04-30 08:26:16 +05:30
Youlun Peng
58431f102c
Set LANCZOS as the default interpolation for image resizing in ControlNet training ( #11449 )
...
Set LANCZOS as the default interpolation for image resizing
2025-04-29 08:47:02 -04:00
urpetkov-amd
4a9ab650aa
Fixing missing provider options argument ( #11397 )
...
* Fixing missing provider options argument
* Adding if else for provider options
* Apply suggestions from code review
Co-authored-by: YiYi Xu <yixu310@gmail.com >
* Apply style fixes
* Update src/diffusers/pipelines/onnx_utils.py
Co-authored-by: YiYi Xu <yixu310@gmail.com >
* Update src/diffusers/pipelines/onnx_utils.py
Co-authored-by: YiYi Xu <yixu310@gmail.com >
---------
Co-authored-by: Uros Petkovic <urpektov@amd.com >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-28 10:23:05 -10:00
Linoy Tsaban
0ac1d5b482
[Hi-Dream LoRA] fix bug in validation ( #11439 )
...
remove unnecessary pipeline moving to cpu in validation
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2025-04-28 06:22:32 -10:00
Yao Matrix
7567adfc45
enable 28 GGUF test cases on XPU ( #11404 )
...
* enable gguf test cases on XPU
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
* make SD35LargeGGUFSingleFileTests::test_pipeline_inference pas
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com >
* make FluxControlLoRAGGUFTests::test_lora_loading pass
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* polish code
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* Apply style fixes
---------
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
Signed-off-by: root <root@a4bf01945cfe.jf.intel.com >
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
Co-authored-by: root <root@a4bf01945cfe.jf.intel.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-28 21:32:04 +05:30
tongyu
3da98e7ee3
[train_text_to_image_lora] Better image interpolation in training scripts follow up ( #11427 )
...
* Update train_text_to_image_lora.py
* update_train_text_to_image_lora
2025-04-28 11:23:24 -04:00
tongyu
b3b04fefde
[train_text_to_image] Better image interpolation in training scripts follow up ( #11426 )
...
* Update train_text_to_image.py
* update
2025-04-28 10:50:33 -04:00
Sayak Paul
0e3f2713c2
[tests] fix import. ( #11434 )
...
fix import.
2025-04-28 13:32:28 +08:00
Yao Matrix
a7e9f85e21
enable test_layerwise_casting_memory cases on XPU ( #11406 )
...
* enable test_layerwise_casting_memory cases on XPU
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-28 06:38:39 +05:30
Yao Matrix
9ce89e2efa
enable group_offload cases and quanto cases on XPU ( #11405 )
...
* enable group_offload cases and quanto cases on XPU
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
* use backend APIs
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
---------
Signed-off-by: YAO Matrix <matrix.yao@intel.com >
Signed-off-by: Yao Matrix <matrix.yao@intel.com >
2025-04-28 06:37:16 +05:30
Sayak Paul
aa5f5d41d6
[tests] add tests to check for graph breaks, recompilation, cuda syncs in pipelines during torch.compile() ( #11085 )
...
* test for better torch.compile stuff.
* fixes
* recompilation and graph break.
* clear compilation cache.
* change to modeling level test.
* allow running compilation tests during nightlies.
2025-04-28 08:36:33 +08:00
Mert Erbak
bd96a084d3
[train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing ( #11421 )
...
* Set LANCZOS as default interpolation mode for resizing
* [train_dreambooth_lora.py] Set LANCZOS as default interpolation mode for resizing
2025-04-26 01:58:41 -04:00
Aryan
b863bdd6ca
Modular Diffusers Guiders ( #11311 )
...
* cfg; slg; pag; sdxl without controlnet
* support sdxl controlnet
* support controlnet union
* update
* update
* cfg zero*
* use unwrap_module for torch compiled modules
* remove guider kwargs
* remove commented code
* remove old guider
* fix slg bug
* remove debug print
* autoguidance
* smoothed energy guidance
* add note about seg
* tangential cfg
* cfg plus plus
* support cfgpp in ddim
* apply review suggestions
* refactor
* rename enable/disable
* remove cfg++ for now
* rename do_classifier_free_guidance->prepare_unconditional_embeds
* remove unused
2025-04-26 03:42:42 +05:30
co63oc
f00a995753
Fix typos in strings and comments ( #11407 )
2025-04-24 08:53:47 -10:00
Ishan Modi
e8312e7ca9
[BUG] fixed WAN docstring ( #11226 )
...
update
2025-04-24 08:49:37 -10:00
Emiliano
7986834572
Fix Flux IP adapter argument in the pipeline example ( #11402 )
...
Fix Flux IP adapter argument in the example
IP-Adapter example had a wrong argument. Fix `true_cfg` -> `true_cfg_scale`
2025-04-24 08:41:12 -10:00
Linoy Tsaban
edd7880418
[HiDream LoRA] optimizations + small updates ( #11381 )
...
* 1. add pre-computation of prompt embeddings when custom prompts are used as well
2. save model card even if model is not pushed to hub
3. remove scheduler initialization from code example - not necessary anymore (it's now if the base model's config)
4. add skip_final_inference - to allow to run with validation, but skip the final loading of the pipeline with the lora weights to reduce memory reqs
* pre encode validation prompt as well
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* pre encode validation prompt as well
* Apply style fixes
* empty commit
* change default trained modules
* empty commit
* address comments + change encoding of validation prompt (before it was only pre-encoded if custom prompts are provided, but should be pre-encoded either way)
* Apply style fixes
* empty commit
* fix validation_embeddings definition
* fix final inference condition
* fix pipeline deletion in last inference
* Apply style fixes
* empty commit
* layers
* remove readme remarks on only pre-computing when instance prompt is provided and change example to 3d icons
* smol fix
* empty commit
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-24 07:48:19 +03:00
Teriks
b4be42282d
Kolors additional pipelines, community contrib ( #11372 )
...
* Kolors additional pipelines, community contrib
---------
Co-authored-by: Teriks <Teriks@users.noreply.github.com >
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com >
2025-04-23 11:07:27 -10:00
Ishan Modi
a4f9c3cbc3
[Feature] Added Xlab Controlnet support ( #11249 )
...
update
2025-04-23 10:43:50 -10:00
Ishan Dutta
4b60f4b602
[train_dreambooth_flux] Add LANCZOS as the default interpolation mode for image resizing ( #11395 )
2025-04-23 10:47:05 -04:00
Aryan
6cef71de3a
Fix group offloading with block_level and use_stream=True ( #11375 )
...
* fix
* add tests
* add message check
2025-04-23 18:17:53 +05:30
Ameer Azam
026507c06c
Update README_hidream.md ( #11386 )
...
Small change
requirements_sana.txt to
requirements_hidream.txt
2025-04-22 20:08:26 -04:00
YiYi Xu
448c72a230
[HiDream] move deprecation to 0.35.0 ( #11384 )
...
up
2025-04-22 08:08:08 -10:00
Aryan
f108ad8888
Update modeling imports ( #11129 )
...
update
2025-04-22 06:59:25 -10:00
Linoy Tsaban
e30d3bf544
[LoRA] add LoRA support to HiDream and fine-tuning script ( #11281 )
...
* initial commit
* initial commit
* initial commit
* initial commit
* initial commit
* initial commit
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com >
* move prompt embeds, pooled embeds outside
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: hlky <hlky@hlky.ac >
* fix import
* fix import and tokenizer 4, text encoder 4 loading
* te
* prompt embeds
* fix naming
* shapes
* initial commit to add HiDreamImageLoraLoaderMixin
* fix init
* add tests
* loader
* fix model input
* add code example to readme
* fix default max length of text encoders
* prints
* nullify training cond in unpatchify for temp fix to incompatible shaping of transformer output during training
* smol fix
* unpatchify
* unpatchify
* fix validation
* flip pred and loss
* fix shift!!!
* revert unpatchify changes (for now)
* smol fix
* Apply style fixes
* workaround moe training
* workaround moe training
* remove prints
* to reduce some memory, keep vae in `weight_dtype` same as we have for flux (as it's the same vae)
https://github.com/huggingface/diffusers/blob/bbd0c161b55ba2234304f1e6325832dd69c60565/examples/dreambooth/train_dreambooth_lora_flux.py#L1207
* refactor to align with HiDream refactor
* refactor to align with HiDream refactor
* refactor to align with HiDream refactor
* add support for cpu offloading of text encoders
* Apply style fixes
* adjust lr and rank for train example
* fix copies
* Apply style fixes
* update README
* update README
* update README
* fix license
* keep prompt2,3,4 as None in validation
* remove reverse ode comment
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* vae offload change
* fix text encoder offloading
* Apply style fixes
* cleaner to_kwargs
* fix module name in copied from
* add requirements
* fix offloading
* fix offloading
* fix offloading
* update transformers version in reqs
* try AutoTokenizer
* try AutoTokenizer
* Apply style fixes
* empty commit
* Delete tests/lora/test_lora_layers_hidream.py
* change tokenizer_4 to load with AutoTokenizer as well
* make text_encoder_four and tokenizer_four configurable
* save model card
* save model card
* revert T5
* fix test
* remove non diffusers lumina2 conversion
---------
Co-authored-by: Bagheera <59658056+bghira@users.noreply.github.com >
Co-authored-by: hlky <hlky@hlky.ac >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-04-22 11:44:02 +03:00
apolinário
6ab62c7431
Add stochastic sampling to FlowMatchEulerDiscreteScheduler ( #11369 )
...
* Add stochastic sampling to FlowMatchEulerDiscreteScheduler
This PR adds stochastic sampling to FlowMatchEulerDiscreteScheduler based on https://github.com/Lightricks/LTX-Video/commit/b1aeddd7ccac85e6d1b0d97762610ddb53c1b408 ltx_video/schedulers/rf.py
* Apply style fixes
* Use config value directly
* Apply style fixes
* Swap order
* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py
Co-authored-by: YiYi Xu <yixu310@gmail.com >
* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py
Co-authored-by: YiYi Xu <yixu310@gmail.com >
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2025-04-21 17:18:30 -10:00
yiyixuxu
d143851309
move methods to blocks
2025-04-12 11:46:25 +02:00
yiyixuxu
9ad1470d48
up
2025-04-11 18:29:21 +02:00
yiyixuxu
bf99ab2f55
up
2025-04-09 20:36:45 +02:00
yiyixuxu
ee842839ef
add componentspec and configspec
2025-04-09 01:40:02 +02:00
YiYi Xu
96795afc72
Merge branch 'main' into modular-diffusers
2025-04-07 18:05:00 -10:00
yiyixuxu
12650e1393
up
2025-02-04 02:08:28 +01:00
yiyixuxu
addaad013c
more more more refactor
2025-02-03 20:36:05 +01:00
yiyixuxu
485f8d1758
more refactor
2025-02-01 21:30:05 +01:00
yiyixuxu
cff0fd6260
more refactor
2025-02-01 11:36:13 +01:00
yiyixuxu
8ddb20bfb8
up
2025-02-01 05:45:00 +01:00
yiyixuxu
e5089d702b
update
2025-01-31 21:55:45 +01:00
yiyixuxu
2c3e4eafa8
fix
2025-01-29 17:58:40 +01:00
yiyixuxu
c7020df2cf
add model_info
2025-01-27 11:33:27 +01:00
yiyixuxu
4bed3e306e
up up
2025-01-26 13:04:33 +01:00
yiyixuxu
00a3bc9d6c
fix
2025-01-23 18:16:00 +01:00
YiYi Xu
ccb35acd81
Merge branch 'main' into modular-diffusers
2025-01-23 07:07:11 -10:00
yiyixuxu
00cae4e857
docstring doc doc doc
2025-01-23 11:07:13 +01:00
yiyixuxu
b3fb4188f5
Merge branch 'modular-diffusers' of github.com:huggingface/diffusers into modular-diffusers
2025-01-22 17:24:06 +01:00
YiYi Xu
71df1581f7
Update src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_modular.py
...
Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com >
2025-01-22 06:19:22 -10:00
yiyixuxu
d046cf7d35
block state + fix for num_images_per_prompt > 1 for denoise/controlnet union etc
2025-01-22 09:48:57 +01:00
yiyixuxu
68a5185c86
refactor more, ipadapter node, lora node
2025-01-20 03:36:01 +01:00
yiyixuxu
6e2fe26bfd
fix more for lora
2025-01-18 08:04:12 +01:00
yiyixuxu
77b5fa59c5
make it work with lora has both text_encoder & unet
2025-01-18 04:12:07 +01:00
yiyixuxu
a226920b52
get_block_state make it less verbose
2025-01-17 01:37:18 +01:00
yiyixuxu
7007f72409
InputParam, OutputParam, get_auto_doc
2025-01-16 11:44:24 +01:00
yiyixuxu
a6804de4a2
add controlnet union to auto & fix for pag
2025-01-12 16:24:01 +01:00
yiyixuxu
7f897a9fc4
fix
2025-01-12 04:50:45 +01:00
yiyixuxu
0966663d2a
adjust print
2025-01-11 19:15:54 +01:00
yiyixuxu
fb78f4f12d
Merge branch 'modular-diffusers' of github.com:huggingface/diffusers into modular-diffusers
2025-01-11 09:05:56 +01:00
yiyixuxu
2220af6940
refactor
2025-01-11 09:05:47 +01:00
hlky
7a34832d52
[modular] Stable Diffusion XL ControlNet Union ( #10509 )
...
StableDiffusionXLControlNetUnionDenoiseStep
2025-01-09 10:29:45 -10:00
yiyixuxu
e973de64f9
fix contro;net inpaint preprocess
2025-01-08 21:47:20 +01:00
yiyixuxu
db94ca882d
add controlnet inpaint + more refactor
2025-01-07 20:49:58 +01:00
yiyixuxu
6985906a2e
controlnet input & remove the MultiPipelineBlocks class
2025-01-07 01:56:33 +01:00
yiyixuxu
54f410db6c
add inpaint
2025-01-06 09:19:59 +01:00
yiyixuxu
c12a05b9c1
update to to not assume pipeline has hf_device_map
2025-01-03 20:57:44 +01:00
yiyixuxu
2e0f5c86cc
start to add inpaint
2025-01-03 18:20:39 +01:00
yiyixuxu
1d63306295
make it work with lora
2025-01-03 06:07:25 +01:00
yiyixuxu
6c93626f6f
remove run_blocks, just use __call__
2025-01-02 00:59:12 +01:00
yiyixuxu
72c5bf07c8
add a from_block class method to modular pipeline
2025-01-02 00:49:34 +01:00
yiyixuxu
ed59f90f15
modular pipeline builder -> ModularPipeline
2025-01-01 22:15:48 +01:00
yiyixuxu
a09ca7f27e
refactors: block __init__ no longer accept args. remove update_states from pipeline blocks, add update_states to modularpipeline, remove multi-block support for modular pipeline, remove offload support on modular pipeline
2025-01-01 21:43:20 +01:00
yiyixuxu
8c02572e16
add memory_reserve_margin arg to auto offload
2024-12-31 20:08:53 +01:00
yiyixuxu
27dde51de8
add output arg to run_blocks
2024-12-31 18:06:44 +01:00
yiyixuxu
10d4a775f1
style
2024-12-31 09:55:50 +01:00
yiyixuxu
72d9a81d99
components manager
2024-12-31 09:54:46 +01:00
yiyixuxu
4fa85c7963
add model_manager and global offloading method
2024-12-31 02:57:42 +01:00
YiYi Xu
806e8e66fb
Merge branch 'main' into modular-diffusers
2024-12-29 00:44:43 -10:00
yiyixuxu
0b90051db8
add vae encoder node
2024-12-19 17:57:12 +01:00
yiyixuxu
b305c779b2
add offload support!
2024-12-14 21:37:21 +01:00
yiyixuxu
2b3cd2d39c
update
2024-12-14 03:02:31 +01:00
yiyixuxu
bc3d1c9ee6
add model_cpu_offload_seq + _exlude_from_cpu_offload
2024-12-14 00:24:15 +01:00
yiyixuxu
e50d614636
only add model as expected_component when the model need to run for the block, currently it's added even when only config is needed
2024-12-11 03:39:39 +01:00
hlky
a8df0f1ffb
Modular APG ( #10173 )
2024-12-10 08:22:42 -10:00
yiyixuxu
ace53e2d2f
update/refactor
2024-12-10 03:41:28 +01:00
yiyixuxu
ffc2992fc2
add autostep (not complete)
2024-11-16 22:42:06 +01:00
yiyixuxu
c70a285c2c
style
2024-10-30 10:33:25 +01:00
yiyixuxu
8b811feece
refactor, from_pretrained, from_pipe, remove_blocks, replace_blocks
2024-10-30 10:13:03 +01:00
yiyixuxu
37e8dc7a59
remove img2img blocksgit status consolidate text2img and img2img
2024-10-28 00:37:48 +01:00
yiyixuxu
024a9f5de3
fix so that run_blocks can work with inputs in the state
2024-10-27 18:52:56 +01:00
yiyixuxu
005195c23e
add
2024-10-27 15:18:10 +01:00
yiyixuxu
6742f160df
up
2024-10-27 14:59:31 +01:00
yiyixuxu
540d303250
refactor guider
2024-10-26 21:17:06 +02:00
yiyixuxu
f1b3036ca1
update pag guider - draft
2024-10-24 00:14:59 +02:00
yiyixuxu
46ec1743a2
refactor guider, remove prepareguidance step to be combinedd into denoisestep
2024-10-23 21:42:40 +02:00
yiyixuxu
70272b1108
combine controlnetstep into contronetdesnoisestep
2024-10-20 19:45:00 +02:00
yiyixuxu
2b6dcbfa1d
fix controlnet
2024-10-20 19:23:37 +02:00
yiyixuxu
af9572d759
controlnet
2024-10-19 12:36:12 +02:00
yiyixuxu
ddea157979
add from_pipe + run_blocks
2024-10-17 20:02:36 +02:00
yiyixuxu
ad3f9a26c0
update img2img, result match
2024-10-17 05:47:15 +02:00
yiyixuxu
e8d0980f9f
add img2img support - output does not match with non-modular pipeline completely yet (look into later)
2024-10-16 20:56:39 +02:00
yiyixuxu
52a7f1cb97
add dataflow info for each block in builder _repr_
2024-10-16 09:04:32 +02:00
yiyixuxu
33f85fadf6
add
2024-10-14 19:16:23 +02:00