GitLab

* ⚡

️ Speed up method `AutoencoderKLWan.clear_cache` by 886%

**Key optimizations:**
- Compute the number of `WanCausalConv3d` modules in each model (`encoder`/`decoder`) **only once during initialization**, store in `self._cached_conv_counts`. This removes unnecessary repeated tree traversals at every `clear_cache` call, which was the main bottleneck (from profiling).
- The internal helper `_count_conv3d_fast` is optimized via a generator expression with `sum` for efficiency.

All comments from the original code are preserved, except for updated or removed local docstrings/comments relevant to changed lines.  
**Function signatures and outputs remain unchanged.**

* Apply style fixes

* Apply suggestions from code review
Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Apply style fixes

---------
Co-authored-by: codeflash-ai[bot] <148906541+codeflash-ai[bot]@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: Aseem Saxena <aseem.bits@gmail.com>

update

* show how metadata stuff should be incorporated in training scripts.

* typing

* fix

---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* fix flux lora loader when return_metadata is true for non-diffusers

* remove annotation

* working state from hameerabbasi and iddl

* working state form hameerabbasi and iddl (transformer)

* working state (normalization)

* working state (embeddings)

* add chroma loader

* add chroma to mappings

* add chroma to transformer init

* take out variant stuff

* get decently far in changing variant stuff

* add chroma init

* make chroma output class

* add chroma transformer to dummy tp

* add chroma to init

* add chroma to init

* fix single file

* update

* update

* add chroma to auto pipeline

* add chroma to pipeline init

* change to chroma transformer

* take out variant from blocks

* swap embedder location

* remove prompt_2

* work on swapping text encoders

* remove mask function

* dont modify mask (for now)

* wrap attn mask

* no attn mask (can't get it to work)

* remove pooled prompt embeds

* change to my own unpooled embeddeer

* fix load

* take pooled projections out of transformer

* ensure correct dtype for chroma embeddings

* update

* use dn6 attn mask + fix true_cfg_scale

* use chroma pipeline output

* use DN6 embeddings

* remove guidance

* remove guidance embed (pipeline)

* remove guidance from embeddings

* don't return length

* dont change dtype

* remove unused stuff, fix up docs

* add chroma autodoc

* add .md (oops)

* initial chroma docs

* undo don't change dtype

* undo arxiv change

unsure why that happened

* fix hf papers regression in more places

* Update docs/source/en/api/pipelines/chroma.md
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* do_cfg -> self.do_classifier_free_guidance

* Update docs/source/en/api/models/chroma_transformer.md
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* Update chroma.md

* Move chroma layers into transformer

* Remove pruned AdaLayerNorms

* Add chroma fast tests

* (untested) batch cond and uncond

* Add # Copied from for shift

* Update # Copied from statements

* update norm imports

* Revert cond + uncond batching

* Add transformer tests

* move chroma test (oops)

* chroma init

* fix chroma pipeline fast tests

* Update src/diffusers/models/transformers/transformer_chroma.py
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* Move Approximator and Embeddings

* Fix auto pipeline + make style, quality

* make style

* Apply style fixes

* switch to new input ids

* fix # Copied from error

* remove # Copied from on protected members

* try to fix import

* fix import

* make fix-copes

* revert style fix

* update chroma transformer params

* update chroma transformer approximator init params

* update to pad tokens

* fix batch inference

* Make more pipeline tests work

* Make most transformer tests work

* fix docs

* make style, make quality

* skip batch tests

* fix test skipping

* fix test skipping again

* fix for tests

* Fix all pipeline test

* update

* push local changes, fix docs

* add encoder test, remove pooled dim

* default proj dim

* fix tests

* fix equal size list input

* update

* push local changes, fix docs

* add encoder test, remove pooled dim

* default proj dim

* fix tests

* fix equal size list input

* Revert "fix equal size list input"

This reverts commit 3fe4ad67d58d83715bc238f8654f5e90bfc5653c.

* update

* update

* update

* update

* update

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* support text-to-image

* update example

* make fix-copies

* support use_flow_sigmas in EDM scheduler instead of maintain cosmos-specific scheduler

* support video-to-world

* update

* rename text2image pipeline

* make fix-copies

* add t2i test

* add test for v2w pipeline

* support edm dpmsolver multistep

* update

* update

* update

* update tests

* fix tests

* safety checker

* make conversion script work without guardrail

* feat: parse metadata from lora state dicts.

* tests

* fix tests

* key renaming

* fix

* smol update

* smol updates

* load metadata.

* automatically save metadata in save_lora_adapter.

* propagate changes.

* changes

* add test to models too.

* tigher tests.

* updates

* fixes

* rename tests.

* sorted.

* Update src/diffusers/loaders/lora_base.py
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* review suggestions.

* removeprefix.

* propagate changes.

* fix-copies

* sd

* docs.

* fixes

* get review ready.

* one more test to catch error.

* change to a different approach.

* fix-copies.

* todo

* sd3

* update

* revert changes in get_peft_kwargs.

* update

* fixes

* fixes

* simplify _load_sft_state_dict_metadata

* update

* style fix

* uipdate

* update

* update

* empty commit

* _pack_dict_with_prefix

* update

* TODO 1.

* todo: 2.

* todo: 3.

* update

* update

* Apply suggestions from code review
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* reraise.

* move argument.

---------
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* update

* make style

* Update src/diffusers/loaders/lora_conversion_utils.py

* add note explaining threshold

* fix: remove redundant indexing

* style

* improve docstrings for wan

* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* make style

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* add clarity in documentation for device_map

* docs

* fix how compiler tester mixins are used.

* propagate

* more

* typo.

* fix tests

* fix order of decroators.

* clarify more.

* more test cases.

* fix doc

* fix device_map docstring in pipeline_utils.

* more examples

* more

* update

* remove code for stuff that is already supported.

* fix stuff.

* start adding compilation tests for quantization.

* fixes

* make common utility.

* modularize.

* add group offloading+compile

* xfail

* update

* Update tests/quantization/test_torch_compile_utils.py
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* fixes

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

* enable torchao cases on XPU
Signed-off-by: Matrix YAO <matrix.yao@intel.com>

* device agnostic APIs
Signed-off-by: YAO Matrix <matrix.yao@intel.com>

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

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

* enable test_torch_compile_recompilation_and_graph_break on XPU
Signed-off-by: YAO Matrix <matrix.yao@intel.com>

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

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

* fix: vae sampling mode

* fix a typo

support Flux Control LoRA with bnb 8bit.

* allow loading from repo with dot in name

* put new arg at the end to avoid breaking compatibility

* add test for loading repo with dot in name

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

* Update pipeline_flux_inpaint.py to fix padding_mask_crop returning only the inpainted area and not the entire image.

* Apply style fixes

* Update src/diffusers/pipelines/flux/pipeline_flux_inpaint.py

* update

* update

* update

* update

* update

* update

* update

* initial support

* make fix-copies

* fix no split modules

* add conversion script

* refactor

* add pipeline test

* refactor

* fix bug with mask

* fix for reference images

* remove print

* update docs

* update slices

* update

* update

* update example

bring PipelineQuantizationConfig at the top of the import chain.

Use float32 for RoPE on MPS in Wan

* Fix typos in strings and comments
Signed-off-by: co63oc <co63oc@users.noreply.github.com>

* Update src/diffusers/hooks/hooks.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update src/diffusers/hooks/hooks.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update layerwise_casting.py

* Apply style fixes

* update

---------
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

Co-authored-by: Aryan <aryan@huggingface.co>

* sana sprint img2img

* fix import

* fix name

* fix image encoding

* fix image encoding

* fix image encoding

* fix image encoding

* fix image encoding

* fix image encoding

* try w/o strength

* try scaling differently

* try with strength

* revert unnecessary changes to scheduler

* revert unnecessary changes to scheduler

* Apply style fixes

* remove comment

* add copy statements

* add copy statements

* add to doc

* add to doc

* add to doc

* add to doc

* Apply style fixes

* empty commit

* fix copies

* fix copies

* fix copies

* fix copies

* fix copies

* docs

* make fix-copies.

* fix doc building error.

* initial commit - add img2img test

* initial commit - add img2img test

* fix import

* fix imports

* Apply style fixes

* empty commit

* remove

* empty commit

* test vocab size

* fix

* fix prompt missing from last commits

* small changes

* fix image processing when input is tensor

* fix order

* Apply style fixes

* empty commit

* fix shape

* remove comment

* image processing

* remove comment

* skip vae tiling test for now

* Apply style fixes

* empty commit

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>

* improve lora fusion tests

* more improvements.

* remove comment

* update

* relax tolerance.

* num_fused_loras as a property
Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>

* updates

* update

* fix

* fix
Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>

* Update src/diffusers/loaders/lora_base.py
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

---------
Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* Adding device choice for npu

* Adding device choice for npu

---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

wip: check if we can make go compile compat

* update

* update

* Apply style fixes

* init test
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* adjust
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* add the variant check when there are no component folders
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* update related test cases
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* update related unit test cases
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* adjust
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>

* Apply style fixes

---------
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* update

* update

* update

* update

* addressed PR comments

* update

* addressed PR comments

* added tests

* addressed PR comments

* updates

* update

* addressed PR comments

* update

* fix style

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* enable several pipeline integration tests on xpu
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

* fix style
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

* update per comments
Signed-off-by: Matrix Yao <matrix.yao@intel.com>

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

* fix peft delete adapters for flux.

* add test

* empty commit

* update

* update

allow string device to be passed to randn_tensor.

* testing

* testing

* testing

* testing

* testing

* i2v

* i2v

* device fix

* testing

* fix

* fix

* fix

* fix

* fix

* Apply style fixes

* empty commit

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* add guidance rescale

* update docs

* support adaptive instance norm filter

* fix custom timesteps support

* add custom timestep example to docs

* add a note about best generation settings being available only in the original repository

* use original org hub ids instead of personal

* make fix-copies

---------
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>