add modular pipeline for qwen-image 2.1

docs/source/en/api/pipelines/qwenimage21.md

@@ -97,6 +97,28 @@ the terminal sigma, which the scheduler appends. Explicit `sigmas` override the
 list determines the number of steps instead of `num_inference_steps`. If neither is provided, the pipeline uses
 `num_inference_steps` to generate the schedule. The scheduler applies its configured processing to either grid.
 
+## Modular
+
+Qwen-Image 2.1 is also available as a [modular pipeline](../../modular_diffusers/overview). The same blocks run
+text-to-image and image-conditioned generation: pass `image` to condition on one or more images. Classifier-free
+guidance is configured through the `guider` component rather than a `true_cfg_scale` call argument, and the prefix KV
+cache is on by default (`use_kv_cache=False` turns it off).
+
+```python
+import torch
+from diffusers import ClassifierFreeGuidance, ModularPipeline
+
+pipe = ModularPipeline.from_pretrained("Qwen/Qwen-Image-2.1")
+pipe.load_components(dtype=torch.bfloat16)
+pipe.to("cuda")
+
+image = pipe(prompt="A capybara wearing a wizard hat, oil painting").images[0]
+
+# Turn classifier-free guidance on for an edit.
+pipe.update_components(guider=ClassifierFreeGuidance(guidance_scale=4.0))
+edited = pipe(prompt="Move it to a snowy mountain top", negative_prompt="blurry", image=image).images[0]
+```
+
 ## QwenImage21Pipeline
 
 [[autodoc]] QwenImage21Pipeline
@@ -106,3 +128,11 @@ list determines the number of steps instead of `num_inference_steps`. If neither
 ## QwenImagePipelineOutput
 
 [[autodoc]] pipelines.qwenimage.pipeline_output.QwenImagePipelineOutput
+
+## QwenImage21ModularPipeline
+
+[[autodoc]] QwenImage21ModularPipeline
+
+## QwenImage21AutoBlocks
+
+[[autodoc]] QwenImage21AutoBlocks

src/diffusers/__init__.py

@@ -566,6 +566,8 @@
             "MiniMaxH3ModularPipeline",
             "MiniMaxMusic3Blocks",
             "MiniMaxMusic3ModularPipeline",
+            "QwenImage21AutoBlocks",
+            "QwenImage21ModularPipeline",
             "QwenImageAutoBlocks",
             "QwenImageEditAutoBlocks",
             "QwenImageEditModularPipeline",
@@ -1438,6 +1440,8 @@
             MiniMaxH3ModularPipeline,
             MiniMaxMusic3Blocks,
             MiniMaxMusic3ModularPipeline,
+            QwenImage21AutoBlocks,
+            QwenImage21ModularPipeline,
             QwenImageAutoBlocks,
             QwenImageEditAutoBlocks,
             QwenImageEditModularPipeline,

src/diffusers/modular_pipelines/__init__.py

@@ -101,6 +101,7 @@
         "QwenImageLayeredModularPipeline",
         "QwenImageLayeredAutoBlocks",
     ]
+    _import_structure["qwenimage21"] = ["QwenImage21AutoBlocks", "QwenImage21ModularPipeline"]
     _import_structure["anima"] = [
         "AnimaAutoBlocks",
         "AnimaModularPipeline",
@@ -226,6 +227,7 @@
             QwenImageLayeredModularPipeline,
             QwenImageModularPipeline,
         )
+        from .qwenimage21 import QwenImage21AutoBlocks, QwenImage21ModularPipeline
         from .stable_diffusion_3 import StableDiffusion3AutoBlocks, StableDiffusion3ModularPipeline
         from .stable_diffusion_xl import StableDiffusionXLAutoBlocks, StableDiffusionXLModularPipeline
         from .wan import (

src/diffusers/modular_pipelines/modular_pipeline.py

@@ -190,6 +190,7 @@ def _helios_pyramid_map_fn(config_dict=None):
         ("qwenimage-edit", _create_default_map_fn("QwenImageEditModularPipeline")),
         ("qwenimage-edit-plus", _create_default_map_fn("QwenImageEditPlusModularPipeline")),
         ("qwenimage-layered", _create_default_map_fn("QwenImageLayeredModularPipeline")),
+        ("qwenimage21", _create_default_map_fn("QwenImage21ModularPipeline")),
         ("anima", _create_default_map_fn("AnimaModularPipeline")),
         ("z-image", _create_default_map_fn("ZImageModularPipeline")),
         ("cosmos3-omni", _create_default_map_fn("Cosmos3OmniModularPipeline")),

src/diffusers/modular_pipelines/qwenimage21/__init__.py

@@ -0,0 +1,47 @@
+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["modular_blocks_qwenimage21"] = ["QwenImage21AutoBlocks"]
+    _import_structure["modular_pipeline"] = ["QwenImage21ModularPipeline"]
+
+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 .modular_blocks_qwenimage21 import QwenImage21AutoBlocks
+        from .modular_pipeline import QwenImage21ModularPipeline
+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)