add import & stype

missing copied from

Author: yiyixuxu

src/diffusers/__init__.py

@@ -495,6 +495,7 @@
             "LTXImageToVideoPipeline",
             "LTXLatentUpsamplePipeline",
             "LTXPipeline",
+            "LucyEditPipeline",
             "Lumina2Pipeline",
             "Lumina2Text2ImgPipeline",
             "LuminaPipeline",
@@ -1149,6 +1150,7 @@
             LTXImageToVideoPipeline,
             LTXLatentUpsamplePipeline,
             LTXPipeline,
+            LucyEditPipeline,
             Lumina2Pipeline,
             Lumina2Text2ImgPipeline,
             LuminaPipeline,

src/diffusers/pipelines/__init__.py

@@ -285,6 +285,7 @@
     ]
     _import_structure["lumina"] = ["LuminaPipeline", "LuminaText2ImgPipeline"]
     _import_structure["lumina2"] = ["Lumina2Pipeline", "Lumina2Text2ImgPipeline"]
+    _import_structure["lucy"] = ["LucyEditPipeline"]
     _import_structure["marigold"].extend(
         [
             "MarigoldDepthPipeline",
@@ -682,6 +683,7 @@
             LEditsPPPipelineStableDiffusionXL,
         )
         from .ltx import LTXConditionPipeline, LTXImageToVideoPipeline, LTXLatentUpsamplePipeline, LTXPipeline
+        from .lucy import LucyEditPipeline
         from .lumina import LuminaPipeline, LuminaText2ImgPipeline
         from .lumina2 import Lumina2Pipeline, Lumina2Text2ImgPipeline
         from .marigold import (

src/diffusers/pipelines/lucy/__init__.py

@@ -1 +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["pipeline_lucy_edit"] = ["LucyEditPipeline"]
+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 *
+    else:
+        from .pipeline_lucy_edit import LucyEditPipeline
+
+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)

src/diffusers/pipelines/lucy/pipeline_lucy_edit.py

@@ -68,12 +68,14 @@
         >>> height = 480
         >>> width = 832
 
+
         >>> # Load video
         >>> def convert_video(video: List[Image.Image]) -> List[Image.Image]:
         ...     video = load_video(url)[:num_frames]
         ...     video = [video[i].resize((width, height)) for i in range(num_frames)]
         ...     return video
 
+
         >>> video = load_video(url, convert_method=convert_video)
 
         >>> # Load model
@@ -90,7 +92,7 @@
         ...     height=480,
         ...     width=832,
         ...     num_frames=81,
-        ...     guidance_scale=5.0
+        ...     guidance_scale=5.0,
         ... ).frames[0]
 
         >>> # Export video
@@ -115,6 +117,7 @@ def prompt_clean(text):
     text = whitespace_clean(basic_clean(text))
     return text
 
+
 # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.retrieve_latents
 def retrieve_latents(
     encoder_output: torch.Tensor, generator: Optional[torch.Generator] = None, sample_mode: str = "sample"
@@ -191,6 +194,7 @@ def __init__(
         self.vae_scale_factor_spatial = self.vae.config.scale_factor_spatial if getattr(self, "vae", None) else 8
         self.video_processor = VideoProcessor(vae_scale_factor=self.vae_scale_factor_spatial)
 
+    # Copied from diffusers.pipelines.wan.pipeline_wan.WanPipeline._get_t5_prompt_embeds
     def _get_t5_prompt_embeds(
         self,
         prompt: Union[str, List[str]] = None,
@@ -232,6 +236,7 @@ def _get_t5_prompt_embeds(
 
         return prompt_embeds
 
+    # Copied from diffusers.pipelines.wan.pipeline_wan.WanPipeline.encode_prompt
     def encode_prompt(
         self,
         prompt: Union[str, List[str]],
@@ -358,7 +363,7 @@ def check_inputs(
 
         if self.config.boundary_ratio is None and guidance_scale_2 is not None:
             raise ValueError("`guidance_scale_2` is only supported when the pipeline's `boundary_ratio` is not None.")
- 
+
         if video is None:
             raise ValueError("`video` is required, received None.")
 
@@ -397,7 +402,9 @@ def prepare_latents(
             latents = latents.to(device)
 
         # Prepare condition latents
-        condition_latents = [retrieve_latents(self.vae.encode(vid.unsqueeze(0)), sample_mode="argmax") for vid in video]
+        condition_latents = [
+            retrieve_latents(self.vae.encode(vid.unsqueeze(0)), sample_mode="argmax") for vid in video
+        ]
 
         condition_latents = torch.cat(condition_latents, dim=0).to(dtype)
 
@@ -411,9 +418,12 @@ def prepare_latents(
         condition_latents = (condition_latents - latents_mean) * latents_std
 
         # Check shapes
-        assert latents.shape == condition_latents.shape, f"Latents shape {latents.shape} does not match expected shape {condition_latents.shape}. Please check the input."
+        assert latents.shape == condition_latents.shape, (
+            f"Latents shape {latents.shape} does not match expected shape {condition_latents.shape}. Please check the input."
+        )
 
         return latents, condition_latents
+
     @property
     def guidance_scale(self):
         return self._guidance_scale
@@ -469,7 +479,7 @@ def __call__(
         The call function to the pipeline for generation.
 
         Args:
-            video (`List[Image.Image]`): 
+            video (`List[Image.Image]`):
                 The video to use as the condition for the video generation.
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, pass `prompt_embeds` instead.
@@ -621,7 +631,6 @@ def __call__(
             latents,
         )
 
-
         mask = torch.ones(latents.shape, dtype=torch.float32, device=device)
 
         # 6. Denoising loop

src/diffusers/utils/dummy_torch_and_transformers_objects.py

@@ -1592,6 +1592,21 @@ def from_pretrained(cls, *args, **kwargs):
         requires_backends(cls, ["torch", "transformers"])
 
 
+class LucyEditPipeline(metaclass=DummyObject):
+    _backends = ["torch", "transformers"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch", "transformers"])
+
+    @classmethod
+    def from_config(cls, *args, **kwargs):
+        requires_backends(cls, ["torch", "transformers"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["torch", "transformers"])
+
+
 class Lumina2Pipeline(metaclass=DummyObject):
     _backends = ["torch", "transformers"]