* [utils] preserve method metadata in apply_forward_hook
Add @functools.wraps to the inner wrapper so it inherits __name__,
__doc__, __module__ and the signature of the wrapped method. Without
this, methods decorated with @apply_forward_hook (e.g. AutoencoderKL's
encode and decode) lose their docstring and signature, so doc-builder
cannot render them through the [[autodoc]] directive and they show up
as "wrapper" with a generic (*args, **kwargs) signature on the live
API docs. The same affects VQModel, ConsistencyDecoderVAE and the
other autoencoders that use the decorator.
Add regression tests asserting that the wrapped method exposes the
right metadata (name, docstring, signature including default values,
__wrapped__) and that the underlying offload hook still fires through
the wrapper.
Fixes#6575
* Trim apply_forward_hook test to a single assertion
`diffusers-cli custom_blocks` only recognized classes whose base was spelled
exactly `ModularPipelineBlocks`, so a `SequentialPipelineBlocks` or
`AutoPipelineBlocks` subclass (the usual thing to publish) was reported as
"could not be retrieved". Accept the composite subclasses as well, and match
on the class name so dotted bases like
`diffusers.modular_pipelines.SequentialPipelineBlocks` work too.
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
fix(image_processor): preserve 3-tuple return contract when mask is None (#14470)
Ensure InpaintProcessor.preprocess returns (image, None, postprocessing_kwargs) when mask is None, preserving the expected 3-tuple return contract and signature consistency across all preprocess branches. Consolidate unit tests into a parameterized test covering with-mask, without-mask, and crop configurations.
* restructure guides as skill references
* reorganize AGENTS.md and references
* clean up
* clean up
* clean up
* fix AGENTS.md references and add check_ai to Makefile
* clean up
* update paths
* clean up
* [CLI] Clean up and improvements to `diffusers-cli`
Modular pipelines:
- `custom_blocks` also writes `modular_model_index.json`, so a packaged repo is
loadable by `ModularPipeline.from_pretrained` (and runnable by `run`), not just
importable as blocks.
- Add `--cpu-offload auto`, which offloads through the pipeline's
`ComponentsManager`, plus `--offload-margin` to set its `memory_reserve_margin`.
- Add `--workflow` passthrough; warn and ignore it on standard pipelines.
- Route `model_index.json` repos whose `_class_name` is modular to the modular path.
Output saving:
- Resolve every media field on the output object (`images`, `frames`, `audios`,
`audio`) instead of the first match, keeping the batch dimension. Fixes video
output being misrouted through the image branch and LTX2's audio being dropped.
- Fix the `output_type="pt"` video transpose: `postprocess_video` returns
`(B, F, C, H, W)`, not `(B, C, F, H, W)`.
- Save `(B, C, samples)` waveforms as multi-channel wavs (StableAudio).
- Write each video's frames to `<stem>-frames/<NNNN>.png`. Frames need no video
backend, so they replace the `.pt` fallback when `export_to_video` fails.
- Report frame directories as a single path so hundreds of frames don't flood the
terminal; `--push-to` and the sandbox download preserve subfolder structure.
- Raise on unrecognized payloads instead of dumping JSON/pickle.
Remote:
- Add `imageio`, `imageio-ffmpeg`, and `peft` to the default sandbox deps.
- Raise sandbox `start_timeout` to 600s; the 120s default expires while a cold node
pulls the pytorch base image.
* Apply suggestion from @sayakpaul
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* update
* update
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* download kernels when users request for it.
* migrate tests/others to pytest
* Revert "download kernels when users request for it."
This reverts commit 6fe34ade6b.
---------
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* Remove JAX/Flax support
Deletes all Flax models, schedulers, pipelines, and loading utilities,
the from_flax loading path, flax/jax packaging extras, Flax CI filters,
Flax training examples, and Flax content in translated docs.
Hub compatibility is preserved: Flax class names in old model_index.json
files are still stripped to their PyTorch equivalents, and *.msgpack
files in repos are still ignored during download.
* Drop Flax class-name remapping from model_index.json loading
Flax-saved checkpoint metadata is no longer recognized: class names like
FlaxStableDiffusionPipeline in model_index.json now fail to resolve
instead of being remapped to their PyTorch equivalents. *.msgpack files
in hub repos are still ignored during download.
* Restore Flax training examples
The example scripts are standalone and still work with diffusers<=0.39.x.
A warning note is added to each Flax README section pointing out the
version requirement now that the library itself no longer ships Flax.
* update
* Repoint scheduler default-config tests off the Flax fixture
* Repoint example training tests off the Flax fixture
* fix(randn_tensor): compare device.type, not torch.device to str, when suppressing MPS info log
When a CPU generator is passed with an MPS target, randn_tensor intentionally skips
the 'generator was on cpu, tensor will be moved to <device>' info log — MPS doesn't
support device-side generators, so the suggestion to create one on MPS would be
misleading. The guard was written as `if device != "mps"`, but a few lines
earlier `device` is coerced to a `torch.device` object, and
`torch.device("mps") == "mps"` is False (torch.device's __eq__ with a string
returns NotImplemented, falling back to identity — they're different types).
Result: the guard is effectively always True, so MPS users get the spurious log
whenever they pass a CPU generator — the opposite of the documented intent.
Fix: compare `device.type` (a str) against "mps". Added a regression test in
tests/others/test_utils.py that exercises both the MPS and non-MPS paths via
`assertLogs` on the diffusers logger.
* refactor: use CaptureLogger instead of assertLogs in randn_tensor test
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* add attention backend tests.
* remove existing tests/others/test_attention_backends.py file
* modify generate_model_tests.py
* remove native.
* account for _keep_in_fp32_modules
* don't skip when exception is raised.
* use is_kernels_available()
* mark with compile.
* move rtol and atol to methods as defaults.
* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* up
* up
* fix(freeu): run FFT in float32 for float16 inputs to avoid ComplexHalf
`fourier_filter` already upcasts `bfloat16` inputs to `float32` before
calling `torch.fft.fftn`, because PyTorch's FFT does not support bf16.
The same is true for `float16`: depending on the PyTorch version,
`fftn` either
- produces the experimental `torch.complex32` (ComplexHalf) dtype and
emits a `UserWarning: ComplexHalf support is experimental`, or
- raises `RuntimeError: Unsupported dtype Half` outright.
Both paths were reachable from FreeU with half-precision models
(e.g. `sd-turbo` + `fp16` + `enable_freeu`) as reported in #12504.
Extend the existing upcast branch to cover `float16` too. The function
already downcasts the result back to `x_in.dtype` at the end, so the
externally observable dtype is unchanged.
Closes#12504.
* Address review: generalize upcast to non-float32 + fix ruff F821
- Apply @sayakpaul's suggestion: use `elif x.dtype != torch.float32:`
so any non-float32 dtype (bf16, fp16, and future half-precision
dtypes) is upcast to float32 before the FFT.
- Drop the `"torch.Tensor"` return annotation on the test helper
that triggered ruff F821 in CI (torch is imported inside the
method body, not at module scope).
* drop python 3.8
* remove list, tuple, dict from typing
* fold Unions into |
* up
* fix a bunch and please me.
* up
* up
* up
* up
* up
* up
* enforce 3.10.0.
* up
* up
* up
* up
* up
* up
* up
* up
* Update setup.py
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* up.
* python 3.10.
* ifx
* up
* up
* up
* up
* final
* up
* fix typing utils.
* up
* up
* up
* up
* up
* up
* fix
* up
* up
* up
* up
* up
* up
* handle modern types.
* up
* up
* fix ip adapter type checking.
* up
* up
* up
* up
* up
* up
* up
* revert docstring changes.
* keep deleted files deleted.
* keep deleted files deleted.
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* Add check for WindowsPath in to_json_string
On Windows, os.path.join returns a WindowsPath. to_json_string does not convert this from a WindowsPath to a string. Added check for WindowsPath to to_json_saveable.
* Remove extraneous convert to string in test_check_path_types (tests/others/test_config.py)
* Fix style issues in tests/others/test_config.py
* Add unit test to test_config.py to verify that PosixPath and WindowsPath (depending on system) both work when converted to JSON
* Remove distinction between PosixPath and WindowsPath in ConfigMixIn.to_json_string(). Conditional now tests for Path, and uses Path.as_posix() to convert to string.
---------
Co-authored-by: Vincent Dovydaitis <vincedovy@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Add support for _foreach operations and non-blocking to EMAModel
* default foreach to false
* add non-blocking EMA offloading to SD1.5 T2I example script
* fix whitespace
* move foreach to cli argument
* linting
* Update README.md re: EMA weight training
* correct args.foreach_ema
* add tests for foreach ema
* code quality
* add foreach to from_pretrained
* default foreach false
* fix linting
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: drhead <a@a.a>
* find & replace all FloatTensors to Tensor
* apply formatting
* Update torch.FloatTensor to torch.Tensor in the remaining files
* formatting
* Fix the rest of the places where FloatTensor is used as well as in documentation
* formatting
* Update new file from FloatTensor to Tensor
