Merge branch 'main' into tighten-compile-quant-tests

Author: sayakpaul

docs/source/en/tutorials/using_peft_for_inference.md

@@ -319,6 +319,19 @@ If you expect to varied resolutions during inference with this feature, then mak
 
 There are still scenarios where recompulation is unavoidable, such as when the hotswapped LoRA targets more layers than the initial adapter. Try to load the LoRA that targets the most layers *first*. For more details about this limitation, refer to the PEFT [hotswapping](https://huggingface.co/docs/peft/main/en/package_reference/hotswap#peft.utils.hotswap.hotswap_adapter) docs.
 
+<details>
+<summary>Technical details of hotswapping</summary>
+
+The [`~loaders.lora_base.LoraBaseMixin.enable_lora_hotswap`] method converts the LoRA scaling factor from floats to torch.tensors and pads the shape of the weights to the largest required shape to avoid reassigning the whole attribute when the data in the weights are replaced.
+
+This is why the `max_rank` argument is important. The results are unchanged even when the values are padded with zeros. Computation may be slower though depending on the padding size.
+
+Since no new LoRA attributes are added, each subsequent LoRA is only allowed to target the same layers, or subset of layers, the first LoRA targets. Choosing the LoRA loading order is important because if the LoRAs target disjoint layers, you may end up creating a dummy LoRA that targets the union of all target layers.
+
+For more implementation details, take a look at the [`hotswap.py`](https://github.com/huggingface/peft/blob/92d65cafa51c829484ad3d95cf71d09de57ff066/src/peft/utils/hotswap.py) file.
+
+</details>
+
 ## Merge
 
 The weights from each LoRA can be merged together to produce a blend of multiple existing styles. There are several methods for merging LoRAs, each of which differ in *how* the weights are merged (may affect generation quality).
@@ -673,4 +686,6 @@ Browse the [LoRA Studio](https://lorastudio.co/models) for different LoRAs to us
 	height="450"
 ></iframe>
 
-You can find additional LoRAs in the [FLUX LoRA the Explorer](https://huggingface.co/spaces/multimodalart/flux-lora-the-explorer) and [LoRA the Explorer](https://huggingface.co/spaces/multimodalart/LoraTheExplorer) Spaces.
+You can find additional LoRAs in the [FLUX LoRA the Explorer](https://huggingface.co/spaces/multimodalart/flux-lora-the-explorer) and [LoRA the Explorer](https://huggingface.co/spaces/multimodalart/LoraTheExplorer) Spaces.
+
+Check out the [Fast LoRA inference for Flux with Diffusers and PEFT](https://huggingface.co/blog/lora-fast) blog post to learn how to optimize LoRA inference with methods like FlashAttention-3 and fp8 quantization.

src/diffusers/__init__.py

@@ -364,6 +364,8 @@
 else:
     _import_structure["modular_pipelines"].extend(
         [
+            "FluxAutoBlocks",
+            "FluxModularPipeline",
             "StableDiffusionXLAutoBlocks",
             "StableDiffusionXLModularPipeline",
             "WanAutoBlocks",
@@ -999,6 +1001,8 @@
         from .utils.dummy_torch_and_transformers_objects import *  # noqa F403
     else:
         from .modular_pipelines import (
+            FluxAutoBlocks,
+            FluxModularPipeline,
             StableDiffusionXLAutoBlocks,
             StableDiffusionXLModularPipeline,
             WanAutoBlocks,

src/diffusers/hooks/_helpers.py

@@ -107,6 +107,7 @@ def _register(cls):
 def _register_attention_processors_metadata():
     from ..models.attention_processor import AttnProcessor2_0
     from ..models.transformers.transformer_cogview4 import CogView4AttnProcessor
+    from ..models.transformers.transformer_flux import FluxAttnProcessor
     from ..models.transformers.transformer_wan import WanAttnProcessor2_0
 
     # AttnProcessor2_0
@@ -132,6 +133,11 @@ def _register_attention_processors_metadata():
             skip_processor_output_fn=_skip_proc_output_fn_Attention_WanAttnProcessor2_0,
         ),
     )
+    # FluxAttnProcessor
+    AttentionProcessorRegistry.register(
+        model_class=FluxAttnProcessor,
+        metadata=AttentionProcessorMetadata(skip_processor_output_fn=_skip_proc_output_fn_Attention_FluxAttnProcessor),
+    )
 
 
 def _register_transformer_blocks_metadata():
@@ -271,4 +277,6 @@ def _skip_attention___ret___hidden_states___encoder_hidden_states(self, *args, *
 _skip_proc_output_fn_Attention_AttnProcessor2_0 = _skip_attention___ret___hidden_states
 _skip_proc_output_fn_Attention_CogView4AttnProcessor = _skip_attention___ret___hidden_states___encoder_hidden_states
 _skip_proc_output_fn_Attention_WanAttnProcessor2_0 = _skip_attention___ret___hidden_states
+# not sure what this is yet.
+_skip_proc_output_fn_Attention_FluxAttnProcessor = _skip_attention___ret___hidden_states
 # fmt: on

src/diffusers/modular_pipelines/__init__.py

@@ -41,6 +41,7 @@
     ]
     _import_structure["stable_diffusion_xl"] = ["StableDiffusionXLAutoBlocks", "StableDiffusionXLModularPipeline"]
     _import_structure["wan"] = ["WanAutoBlocks", "WanModularPipeline"]
+    _import_structure["flux"] = ["FluxAutoBlocks", "FluxModularPipeline"]
     _import_structure["components_manager"] = ["ComponentsManager"]
 
 if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
@@ -51,6 +52,7 @@
         from ..utils.dummy_pt_objects import *  # noqa F403
     else:
         from .components_manager import ComponentsManager
+        from .flux import FluxAutoBlocks, FluxModularPipeline
         from .modular_pipeline import (
             AutoPipelineBlocks,
             BlockState,

src/diffusers/modular_pipelines/flux/__init__.py

@@ -0,0 +1,66 @@
+from typing import TYPE_CHECKING
+
+from ...utils import (
+    DIFFUSERS_SLOW_IMPORT,
+    OptionalDependencyNotAvailable,
+    _LazyModule,
+    get_objects_from_module,
+    is_torch_available,
+    is_transformers_available,
+)
+
+
+_dummy_objects = {}
+_import_structure = {}
+
+try:
+    if not (is_transformers_available() and is_torch_available()):
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    from ...utils import dummy_torch_and_transformers_objects  # noqa F403
+
+    _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_objects))
+else:
+    _import_structure["encoders"] = ["FluxTextEncoderStep"]
+    _import_structure["modular_blocks"] = [
+        "ALL_BLOCKS",
+        "AUTO_BLOCKS",
+        "TEXT2IMAGE_BLOCKS",
+        "FluxAutoBeforeDenoiseStep",
+        "FluxAutoBlocks",
+        "FluxAutoBlocks",
+        "FluxAutoDecodeStep",
+        "FluxAutoDenoiseStep",
+    ]
+    _import_structure["modular_pipeline"] = ["FluxModularPipeline"]
+
+if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
+    try:
+        if not (is_transformers_available() and is_torch_available()):
+            raise OptionalDependencyNotAvailable()
+    except OptionalDependencyNotAvailable:
+        from ...utils.dummy_torch_and_transformers_objects import *  # noqa F403
+    else:
+        from .encoders import FluxTextEncoderStep
+        from .modular_blocks import (
+            ALL_BLOCKS,
+            AUTO_BLOCKS,
+            TEXT2IMAGE_BLOCKS,
+            FluxAutoBeforeDenoiseStep,
+            FluxAutoBlocks,
+            FluxAutoDecodeStep,
+            FluxAutoDenoiseStep,
+        )
+        from .modular_pipeline import FluxModularPipeline
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(
+        __name__,
+        globals()["__file__"],
+        _import_structure,
+        module_spec=__spec__,
+    )
+
+    for name, value in _dummy_objects.items():
+        setattr(sys.modules[__name__], name, value)