diffusers 0.33.1__py3-none-any.whl → 0.35.0__py3-none-any.whl

diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py

@@ -11,7 +11,7 @@ from ...pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyCh
 from ...schedulers import KarrasDiffusionSchedulers
 from ...utils import deprecate, is_torch_xla_available, logging
 from ...utils.torch_utils import randn_tensor
-from ..pipeline_utils import DiffusionPipeline, StableDiffusionMixin
+from ..pipeline_utils import DeprecatedPipelineMixin, DiffusionPipeline, StableDiffusionMixin
 from .pipeline_output import SemanticStableDiffusionPipelineOutput
 
 
@@ -25,7 +25,8 @@ else:
 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name
 
 
-class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
+class SemanticStableDiffusionPipeline(DeprecatedPipelineMixin, DiffusionPipeline, StableDiffusionMixin):
+    _last_supported_version = "0.33.1"
     r"""
     Pipeline for text-to-image generation using Stable Diffusion with latent editing.
 
@@ -129,7 +130,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
     def prepare_extra_step_kwargs(self, generator, eta):
         # prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
         # eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
-        # eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
+        # eta corresponds to η in DDIM paper: https://huggingface.co/papers/2010.02502
         # and should be between [0, 1]
 
         accepts_eta = "eta" in set(inspect.signature(self.scheduler.step).parameters.keys())
@@ -270,8 +271,8 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             num_images_per_prompt (`int`, *optional*, defaults to 1):
                 The number of images to generate per prompt.
             eta (`float`, *optional*, defaults to 0.0):
-                Corresponds to parameter eta (η) from the [DDIM](https://arxiv.org/abs/2010.02502) paper. Only applies
-                to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
+                Corresponds to parameter eta (η) from the [DDIM](https://huggingface.co/papers/2010.02502) paper. Only
+                applies to the [`~schedulers.DDIMScheduler`], and is ignored in other schedulers.
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
                 generation deterministic.
@@ -451,7 +452,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
             edit_concepts = edit_concepts.view(bs_embed_edit * num_images_per_prompt, seq_len_edit, -1)
 
         # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
-        # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
+        # of the Imagen paper: https://huggingface.co/papers/2205.11487 . `guidance_scale = 1`
         # corresponds to doing no classifier free guidance.
         do_classifier_free_guidance = guidance_scale > 1.0
         # get unconditional embeddings for classifier free guidance

diffusers/pipelines/shap_e/camera.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Open AI and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Open AI and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diffusers/pipelines/shap_e/pipeline_shap_e.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Open AI and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Open AI and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diffusers/pipelines/shap_e/pipeline_shap_e_img2img.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Open AI and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Open AI and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.

diffusers/pipelines/shap_e/renderer.py

@@ -1,4 +1,4 @@
-# Copyright 2024 Open AI and The HuggingFace Team. All rights reserved.
+# Copyright 2025 Open AI and The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -54,7 +54,7 @@ def posenc_nerf(x: torch.Tensor, min_deg: int = 0, max_deg: int = 15) -> torch.T
     """
     Concatenate x and its positional encodings, following NeRF.
 
-    Reference: https://arxiv.org/pdf/2210.04628.pdf
+    Reference: https://huggingface.co/papers/2210.04628
     """
     if min_deg == max_deg:
         return x
@@ -1038,7 +1038,7 @@ class ShapERenderer(ModelMixin, ConfigMixin):
         textures = _convert_srgb_to_linear(textures)
         textures = textures.float()
 
-        # 3.3 augument the mesh with texture data
+        # 3.3 augment the mesh with texture data
         assert len(textures.shape) == 3 and textures.shape[-1] == len(texture_channels), (
             f"expected [meta_batch x inner_batch x texture_channels] field results, but got {textures.shape}"
         )

diffusers/pipelines/skyreels_v2/__init__.py

@@ -0,0 +1,59 @@
+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_skyreels_v2"] = ["SkyReelsV2Pipeline"]
+    _import_structure["pipeline_skyreels_v2_diffusion_forcing"] = ["SkyReelsV2DiffusionForcingPipeline"]
+    _import_structure["pipeline_skyreels_v2_diffusion_forcing_i2v"] = [
+        "SkyReelsV2DiffusionForcingImageToVideoPipeline"
+    ]
+    _import_structure["pipeline_skyreels_v2_diffusion_forcing_v2v"] = [
+        "SkyReelsV2DiffusionForcingVideoToVideoPipeline"
+    ]
+    _import_structure["pipeline_skyreels_v2_i2v"] = ["SkyReelsV2ImageToVideoPipeline"]
+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_skyreels_v2 import SkyReelsV2Pipeline
+        from .pipeline_skyreels_v2_diffusion_forcing import SkyReelsV2DiffusionForcingPipeline
+        from .pipeline_skyreels_v2_diffusion_forcing_i2v import SkyReelsV2DiffusionForcingImageToVideoPipeline
+        from .pipeline_skyreels_v2_diffusion_forcing_v2v import SkyReelsV2DiffusionForcingVideoToVideoPipeline
+        from .pipeline_skyreels_v2_i2v import SkyReelsV2ImageToVideoPipeline
+
+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)

diffusers/pipelines/skyreels_v2/pipeline_output.py

@@ -0,0 +1,20 @@
+from dataclasses import dataclass
+
+import torch
+
+from diffusers.utils import BaseOutput
+
+
+@dataclass
+class SkyReelsV2PipelineOutput(BaseOutput):
+    r"""
+    Output class for SkyReelsV2 pipelines.
+
+    Args:
+        frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]):
+            List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing
+            denoised PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape
+            `(batch_size, num_frames, channels, height, width)`.
+    """
+
+    frames: torch.Tensor