diffusers 0.27.0__py3-none-any.whl → 0.32.2__py3-none-any.whl

diffusers/models/vq_model.py

@@ -11,171 +11,19 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from dataclasses import dataclass
-from typing import Optional, Tuple, Union
+from ..utils import deprecate
+from .autoencoders.vq_model import VQEncoderOutput, VQModel
 
-import torch
-import torch.nn as nn
 
-from ..configuration_utils import ConfigMixin, register_to_config
-from ..utils import BaseOutput
-from ..utils.accelerate_utils import apply_forward_hook
-from .autoencoders.vae import Decoder, DecoderOutput, Encoder, VectorQuantizer
-from .modeling_utils import ModelMixin
+class VQEncoderOutput(VQEncoderOutput):
+    def __init__(self, *args, **kwargs):
+        deprecation_message = "Importing `VQEncoderOutput` from `diffusers.models.vq_model` is deprecated and this will be removed in a future version. Please use `from diffusers.models.autoencoders.vq_model import VQEncoderOutput`, instead."
+        deprecate("VQEncoderOutput", "0.31", deprecation_message)
+        super().__init__(*args, **kwargs)
 
 
-@dataclass
-class VQEncoderOutput(BaseOutput):
-    """
-    Output of VQModel encoding method.
-
-    Args:
-        latents (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):
-            The encoded output sample from the last layer of the model.
-    """
-
-    latents: torch.FloatTensor
-
-
-class VQModel(ModelMixin, ConfigMixin):
-    r"""
-    A VQ-VAE model for decoding latent representations.
-
-    This model inherits from [`ModelMixin`]. Check the superclass documentation for it's generic methods implemented
-    for all models (such as downloading or saving).
-
-    Parameters:
-        in_channels (int, *optional*, defaults to 3): Number of channels in the input image.
-        out_channels (int,  *optional*, defaults to 3): Number of channels in the output.
-        down_block_types (`Tuple[str]`, *optional*, defaults to `("DownEncoderBlock2D",)`):
-            Tuple of downsample block types.
-        up_block_types (`Tuple[str]`, *optional*, defaults to `("UpDecoderBlock2D",)`):
-            Tuple of upsample block types.
-        block_out_channels (`Tuple[int]`, *optional*, defaults to `(64,)`):
-            Tuple of block output channels.
-        layers_per_block (`int`, *optional*, defaults to `1`): Number of layers per block.
-        act_fn (`str`, *optional*, defaults to `"silu"`): The activation function to use.
-        latent_channels (`int`, *optional*, defaults to `3`): Number of channels in the latent space.
-        sample_size (`int`, *optional*, defaults to `32`): Sample input size.
-        num_vq_embeddings (`int`, *optional*, defaults to `256`): Number of codebook vectors in the VQ-VAE.
-        norm_num_groups (`int`, *optional*, defaults to `32`): Number of groups for normalization layers.
-        vq_embed_dim (`int`, *optional*): Hidden dim of codebook vectors in the VQ-VAE.
-        scaling_factor (`float`, *optional*, defaults to `0.18215`):
-            The component-wise standard deviation of the trained latent space computed using the first batch of the
-            training set. This is used to scale the latent space to have unit variance when training the diffusion
-            model. The latents are scaled with the formula `z = z * scaling_factor` before being passed to the
-            diffusion model. When decoding, the latents are scaled back to the original scale with the formula: `z = 1
-            / scaling_factor * z`. For more details, refer to sections 4.3.2 and D.1 of the [High-Resolution Image
-            Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2112.10752) paper.
-        norm_type (`str`, *optional*, defaults to `"group"`):
-            Type of normalization layer to use. Can be one of `"group"` or `"spatial"`.
-    """
-
-    @register_to_config
-    def __init__(
-        self,
-        in_channels: int = 3,
-        out_channels: int = 3,
-        down_block_types: Tuple[str, ...] = ("DownEncoderBlock2D",),
-        up_block_types: Tuple[str, ...] = ("UpDecoderBlock2D",),
-        block_out_channels: Tuple[int, ...] = (64,),
-        layers_per_block: int = 1,
-        act_fn: str = "silu",
-        latent_channels: int = 3,
-        sample_size: int = 32,
-        num_vq_embeddings: int = 256,
-        norm_num_groups: int = 32,
-        vq_embed_dim: Optional[int] = None,
-        scaling_factor: float = 0.18215,
-        norm_type: str = "group",  # group, spatial
-        mid_block_add_attention=True,
-        lookup_from_codebook=False,
-        force_upcast=False,
-    ):
-        super().__init__()
-
-        # pass init params to Encoder
-        self.encoder = Encoder(
-            in_channels=in_channels,
-            out_channels=latent_channels,
-            down_block_types=down_block_types,
-            block_out_channels=block_out_channels,
-            layers_per_block=layers_per_block,
-            act_fn=act_fn,
-            norm_num_groups=norm_num_groups,
-            double_z=False,
-            mid_block_add_attention=mid_block_add_attention,
-        )
-
-        vq_embed_dim = vq_embed_dim if vq_embed_dim is not None else latent_channels
-
-        self.quant_conv = nn.Conv2d(latent_channels, vq_embed_dim, 1)
-        self.quantize = VectorQuantizer(num_vq_embeddings, vq_embed_dim, beta=0.25, remap=None, sane_index_shape=False)
-        self.post_quant_conv = nn.Conv2d(vq_embed_dim, latent_channels, 1)
-
-        # pass init params to Decoder
-        self.decoder = Decoder(
-            in_channels=latent_channels,
-            out_channels=out_channels,
-            up_block_types=up_block_types,
-            block_out_channels=block_out_channels,
-            layers_per_block=layers_per_block,
-            act_fn=act_fn,
-            norm_num_groups=norm_num_groups,
-            norm_type=norm_type,
-            mid_block_add_attention=mid_block_add_attention,
-        )
-
-    @apply_forward_hook
-    def encode(self, x: torch.FloatTensor, return_dict: bool = True) -> VQEncoderOutput:
-        h = self.encoder(x)
-        h = self.quant_conv(h)
-
-        if not return_dict:
-            return (h,)
-
-        return VQEncoderOutput(latents=h)
-
-    @apply_forward_hook
-    def decode(
-        self, h: torch.FloatTensor, force_not_quantize: bool = False, return_dict: bool = True, shape=None
-    ) -> Union[DecoderOutput, torch.FloatTensor]:
-        # also go through quantization layer
-        if not force_not_quantize:
-            quant, _, _ = self.quantize(h)
-        elif self.config.lookup_from_codebook:
-            quant = self.quantize.get_codebook_entry(h, shape)
-        else:
-            quant = h
-        quant2 = self.post_quant_conv(quant)
-        dec = self.decoder(quant2, quant if self.config.norm_type == "spatial" else None)
-
-        if not return_dict:
-            return (dec,)
-
-        return DecoderOutput(sample=dec)
-
-    def forward(
-        self, sample: torch.FloatTensor, return_dict: bool = True
-    ) -> Union[DecoderOutput, Tuple[torch.FloatTensor, ...]]:
-        r"""
-        The [`VQModel`] forward method.
-
-        Args:
-            sample (`torch.FloatTensor`): Input sample.
-            return_dict (`bool`, *optional*, defaults to `True`):
-                Whether or not to return a [`models.vq_model.VQEncoderOutput`] instead of a plain tuple.
-
-        Returns:
-            [`~models.vq_model.VQEncoderOutput`] or `tuple`:
-                If return_dict is True, a [`~models.vq_model.VQEncoderOutput`] is returned, otherwise a plain `tuple`
-                is returned.
-        """
-
-        h = self.encode(sample).latents
-        dec = self.decode(h).sample
-
-        if not return_dict:
-            return (dec,)
-
-        return DecoderOutput(sample=dec)
+class VQModel(VQModel):
+    def __init__(self, *args, **kwargs):
+        deprecation_message = "Importing `VQModel` from `diffusers.models.vq_model` is deprecated and this will be removed in a future version. Please use `from diffusers.models.autoencoders.vq_model import VQModel`, instead."
+        deprecate("VQModel", "0.31", deprecation_message)
+        super().__init__(*args, **kwargs)

diffusers/optimization.py

@@ -87,7 +87,7 @@ def get_piecewise_constant_schedule(optimizer: Optimizer, step_rules: str, last_
             The optimizer for which to schedule the learning rate.
         step_rules (`string`):
             The rules for the learning rate. ex: rule_steps="1:10,0.1:20,0.01:30,0.005" it means that the learning rate
-            if multiple 1 for the first 10 steps, mutiple 0.1 for the next 20 steps, multiple 0.01 for the next 30
+            if multiple 1 for the first 10 steps, multiple 0.1 for the next 20 steps, multiple 0.01 for the next 30
             steps and multiple 0.005 for the other steps.
         last_epoch (`int`, *optional*, defaults to -1):
             The index of the last epoch when resuming training.

diffusers/pipelines/__init__.py

@@ -10,6 +10,7 @@ from ..utils import (
     is_librosa_available,
     is_note_seq_available,
     is_onnx_available,
+    is_sentencepiece_available,
     is_torch_available,
     is_torch_npu_available,
     is_transformers_available,
@@ -20,10 +21,14 @@ from ..utils import (
 _dummy_objects = {}
 _import_structure = {
     "controlnet": [],
+    "controlnet_hunyuandit": [],
+    "controlnet_sd3": [],
     "controlnet_xs": [],
     "deprecated": [],
     "latent_diffusion": [],
     "ledits_pp": [],
+    "marigold": [],
+    "pag": [],
     "stable_diffusion": [],
     "stable_diffusion_xl": [],
 }
@@ -111,10 +116,29 @@ else:
             "VersatileDiffusionTextToImagePipeline",
         ]
     )
+    _import_structure["allegro"] = ["AllegroPipeline"]
     _import_structure["amused"] = ["AmusedImg2ImgPipeline", "AmusedInpaintPipeline", "AmusedPipeline"]
     _import_structure["animatediff"] = [
         "AnimateDiffPipeline",
+        "AnimateDiffControlNetPipeline",
+        "AnimateDiffSDXLPipeline",
+        "AnimateDiffSparseControlNetPipeline",
         "AnimateDiffVideoToVideoPipeline",
+        "AnimateDiffVideoToVideoControlNetPipeline",
+    ]
+    _import_structure["flux"] = [
+        "FluxControlPipeline",
+        "FluxControlInpaintPipeline",
+        "FluxControlImg2ImgPipeline",
+        "FluxControlNetPipeline",
+        "FluxControlNetImg2ImgPipeline",
+        "FluxControlNetInpaintPipeline",
+        "FluxImg2ImgPipeline",
+        "FluxInpaintPipeline",
+        "FluxPipeline",
+        "FluxFillPipeline",
+        "FluxPriorReduxPipeline",
+        "ReduxImageEncoder",
     ]
     _import_structure["audioldm"] = ["AudioLDMPipeline"]
     _import_structure["audioldm2"] = [
@@ -123,6 +147,13 @@ else:
         "AudioLDM2UNet2DConditionModel",
     ]
     _import_structure["blip_diffusion"] = ["BlipDiffusionPipeline"]
+    _import_structure["cogvideo"] = [
+        "CogVideoXPipeline",
+        "CogVideoXImageToVideoPipeline",
+        "CogVideoXVideoToVideoPipeline",
+        "CogVideoXFunControlPipeline",
+    ]
+    _import_structure["cogview3"] = ["CogView3PlusPipeline"]
     _import_structure["controlnet"].extend(
         [
             "BlipDiffusionControlNetPipeline",
@@ -132,6 +163,47 @@ else:
             "StableDiffusionXLControlNetImg2ImgPipeline",
             "StableDiffusionXLControlNetInpaintPipeline",
             "StableDiffusionXLControlNetPipeline",
+            "StableDiffusionXLControlNetUnionPipeline",
+            "StableDiffusionXLControlNetUnionInpaintPipeline",
+            "StableDiffusionXLControlNetUnionImg2ImgPipeline",
+        ]
+    )
+    _import_structure["pag"].extend(
+        [
+            "StableDiffusionControlNetPAGInpaintPipeline",
+            "AnimateDiffPAGPipeline",
+            "KolorsPAGPipeline",
+            "HunyuanDiTPAGPipeline",
+            "StableDiffusion3PAGPipeline",
+            "StableDiffusion3PAGImg2ImgPipeline",
+            "StableDiffusionPAGPipeline",
+            "StableDiffusionPAGImg2ImgPipeline",
+            "StableDiffusionPAGInpaintPipeline",
+            "StableDiffusionControlNetPAGPipeline",
+            "StableDiffusionXLPAGPipeline",
+            "StableDiffusionXLPAGInpaintPipeline",
+            "StableDiffusionXLControlNetPAGImg2ImgPipeline",
+            "StableDiffusionXLControlNetPAGPipeline",
+            "StableDiffusionXLPAGImg2ImgPipeline",
+            "PixArtSigmaPAGPipeline",
+            "SanaPAGPipeline",
+        ]
+    )
+    _import_structure["controlnet_xs"].extend(
+        [
+            "StableDiffusionControlNetXSPipeline",
+            "StableDiffusionXLControlNetXSPipeline",
+        ]
+    )
+    _import_structure["controlnet_hunyuandit"].extend(
+        [
+            "HunyuanDiTControlNetPipeline",
+        ]
+    )
+    _import_structure["controlnet_sd3"].extend(
+        [
+            "StableDiffusion3ControlNetPipeline",
+            "StableDiffusion3ControlNetInpaintingPipeline",
         ]
     )
     _import_structure["deepfloyd_if"] = [
@@ -142,6 +214,8 @@ else:
         "IFPipeline",
         "IFSuperResolutionPipeline",
     ]
+    _import_structure["hunyuandit"] = ["HunyuanDiTPipeline"]
+    _import_structure["hunyuan_video"] = ["HunyuanVideoPipeline"]
     _import_structure["kandinsky"] = [
         "KandinskyCombinedPipeline",
         "KandinskyImg2ImgCombinedPipeline",
@@ -178,12 +252,27 @@ else:
             "LEditsPPPipelineStableDiffusionXL",
         ]
     )
+    _import_structure["latte"] = ["LattePipeline"]
+    _import_structure["ltx"] = ["LTXPipeline", "LTXImageToVideoPipeline"]
+    _import_structure["lumina"] = ["LuminaText2ImgPipeline"]
+    _import_structure["marigold"].extend(
+        [
+            "MarigoldDepthPipeline",
+            "MarigoldNormalsPipeline",
+        ]
+    )
+    _import_structure["mochi"] = ["MochiPipeline"]
     _import_structure["musicldm"] = ["MusicLDMPipeline"]
     _import_structure["paint_by_example"] = ["PaintByExamplePipeline"]
     _import_structure["pia"] = ["PIAPipeline"]
-    _import_structure["pixart_alpha"] = ["PixArtAlphaPipeline"]
+    _import_structure["pixart_alpha"] = ["PixArtAlphaPipeline", "PixArtSigmaPipeline"]
+    _import_structure["sana"] = ["SanaPipeline"]
     _import_structure["semantic_stable_diffusion"] = ["SemanticStableDiffusionPipeline"]
     _import_structure["shap_e"] = ["ShapEImg2ImgPipeline", "ShapEPipeline"]
+    _import_structure["stable_audio"] = [
+        "StableAudioProjectionModel",
+        "StableAudioPipeline",
+    ]
     _import_structure["stable_cascade"] = [
         "StableCascadeCombinedPipeline",
         "StableCascadeDecoderPipeline",
@@ -205,6 +294,12 @@ else:
             "StableDiffusionLDM3DPipeline",
         ]
     )
+    _import_structure["aura_flow"] = ["AuraFlowPipeline"]
+    _import_structure["stable_diffusion_3"] = [
+        "StableDiffusion3Pipeline",
+        "StableDiffusion3Img2ImgPipeline",
+        "StableDiffusion3InpaintPipeline",
+    ]
     _import_structure["stable_diffusion_attend_and_excite"] = ["StableDiffusionAttendAndExcitePipeline"]
     _import_structure["stable_diffusion_safe"] = ["StableDiffusionPipelineSafe"]
     _import_structure["stable_diffusion_sag"] = ["StableDiffusionSAGPipeline"]
@@ -288,6 +383,22 @@ else:
         "StableDiffusionKDiffusionPipeline",
         "StableDiffusionXLKDiffusionPipeline",
     ]
+
+try:
+    if not (is_torch_available() and is_transformers_available() and is_sentencepiece_available()):
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    from ..utils import (
+        dummy_torch_and_transformers_and_sentencepiece_objects,
+    )
+
+    _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_and_sentencepiece_objects))
+else:
+    _import_structure["kolors"] = [
+        "KolorsPipeline",
+        "KolorsImg2ImgPipeline",
+    ]
+
 try:
     if not is_flax_available():
         raise OptionalDependencyNotAvailable()
@@ -360,15 +471,31 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
     except OptionalDependencyNotAvailable:
         from ..utils.dummy_torch_and_transformers_objects import *
     else:
+        from .allegro import AllegroPipeline
         from .amused import AmusedImg2ImgPipeline, AmusedInpaintPipeline, AmusedPipeline
-        from .animatediff import AnimateDiffPipeline, AnimateDiffVideoToVideoPipeline
+        from .animatediff import (
+            AnimateDiffControlNetPipeline,
+            AnimateDiffPipeline,
+            AnimateDiffSDXLPipeline,
+            AnimateDiffSparseControlNetPipeline,
+            AnimateDiffVideoToVideoControlNetPipeline,
+            AnimateDiffVideoToVideoPipeline,
+        )
         from .audioldm import AudioLDMPipeline
         from .audioldm2 import (
             AudioLDM2Pipeline,
             AudioLDM2ProjectionModel,
             AudioLDM2UNet2DConditionModel,
         )
+        from .aura_flow import AuraFlowPipeline
         from .blip_diffusion import BlipDiffusionPipeline
+        from .cogvideo import (
+            CogVideoXFunControlPipeline,
+            CogVideoXImageToVideoPipeline,
+            CogVideoXPipeline,
+            CogVideoXVideoToVideoPipeline,
+        )
+        from .cogview3 import CogView3PlusPipeline
         from .controlnet import (
             BlipDiffusionControlNetPipeline,
             StableDiffusionControlNetImg2ImgPipeline,
@@ -377,6 +504,17 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableDiffusionXLControlNetImg2ImgPipeline,
             StableDiffusionXLControlNetInpaintPipeline,
             StableDiffusionXLControlNetPipeline,
+            StableDiffusionXLControlNetUnionImg2ImgPipeline,
+            StableDiffusionXLControlNetUnionInpaintPipeline,
+            StableDiffusionXLControlNetUnionPipeline,
+        )
+        from .controlnet_hunyuandit import (
+            HunyuanDiTControlNetPipeline,
+        )
+        from .controlnet_sd3 import StableDiffusion3ControlNetInpaintingPipeline, StableDiffusion3ControlNetPipeline
+        from .controlnet_xs import (
+            StableDiffusionControlNetXSPipeline,
+            StableDiffusionXLControlNetXSPipeline,
         )
         from .deepfloyd_if import (
             IFImg2ImgPipeline,
@@ -400,6 +538,22 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             VersatileDiffusionTextToImagePipeline,
             VQDiffusionPipeline,
         )
+        from .flux import (
+            FluxControlImg2ImgPipeline,
+            FluxControlInpaintPipeline,
+            FluxControlNetImg2ImgPipeline,
+            FluxControlNetInpaintPipeline,
+            FluxControlNetPipeline,
+            FluxControlPipeline,
+            FluxFillPipeline,
+            FluxImg2ImgPipeline,
+            FluxInpaintPipeline,
+            FluxPipeline,
+            FluxPriorReduxPipeline,
+            ReduxImageEncoder,
+        )
+        from .hunyuan_video import HunyuanVideoPipeline
+        from .hunyuandit import HunyuanDiTPipeline
         from .i2vgen_xl import I2VGenXLPipeline
         from .kandinsky import (
             KandinskyCombinedPipeline,
@@ -431,18 +585,47 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             LatentConsistencyModelPipeline,
         )
         from .latent_diffusion import LDMTextToImagePipeline
+        from .latte import LattePipeline
         from .ledits_pp import (
             LEditsPPDiffusionPipelineOutput,
             LEditsPPInversionPipelineOutput,
             LEditsPPPipelineStableDiffusion,
             LEditsPPPipelineStableDiffusionXL,
         )
+        from .ltx import LTXImageToVideoPipeline, LTXPipeline
+        from .lumina import LuminaText2ImgPipeline
+        from .marigold import (
+            MarigoldDepthPipeline,
+            MarigoldNormalsPipeline,
+        )
+        from .mochi import MochiPipeline
         from .musicldm import MusicLDMPipeline
+        from .pag import (
+            AnimateDiffPAGPipeline,
+            HunyuanDiTPAGPipeline,
+            KolorsPAGPipeline,
+            PixArtSigmaPAGPipeline,
+            SanaPAGPipeline,
+            StableDiffusion3PAGImg2ImgPipeline,
+            StableDiffusion3PAGPipeline,
+            StableDiffusionControlNetPAGInpaintPipeline,
+            StableDiffusionControlNetPAGPipeline,
+            StableDiffusionPAGImg2ImgPipeline,
+            StableDiffusionPAGInpaintPipeline,
+            StableDiffusionPAGPipeline,
+            StableDiffusionXLControlNetPAGImg2ImgPipeline,
+            StableDiffusionXLControlNetPAGPipeline,
+            StableDiffusionXLPAGImg2ImgPipeline,
+            StableDiffusionXLPAGInpaintPipeline,
+            StableDiffusionXLPAGPipeline,
+        )
         from .paint_by_example import PaintByExamplePipeline
         from .pia import PIAPipeline
-        from .pixart_alpha import PixArtAlphaPipeline
+        from .pixart_alpha import PixArtAlphaPipeline, PixArtSigmaPipeline
+        from .sana import SanaPipeline
         from .semantic_stable_diffusion import SemanticStableDiffusionPipeline
         from .shap_e import ShapEImg2ImgPipeline, ShapEPipeline
+        from .stable_audio import StableAudioPipeline, StableAudioProjectionModel
         from .stable_cascade import (
             StableCascadeCombinedPipeline,
             StableCascadeDecoderPipeline,
@@ -461,6 +644,11 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             StableUnCLIPImg2ImgPipeline,
             StableUnCLIPPipeline,
         )
+        from .stable_diffusion_3 import (
+            StableDiffusion3Img2ImgPipeline,
+            StableDiffusion3InpaintPipeline,
+            StableDiffusion3Pipeline,
+        )
         from .stable_diffusion_attend_and_excite import StableDiffusionAttendAndExcitePipeline
         from .stable_diffusion_diffedit import StableDiffusionDiffEditPipeline
         from .stable_diffusion_gligen import StableDiffusionGLIGENPipeline, StableDiffusionGLIGENTextImagePipeline
@@ -532,6 +720,17 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
                 StableDiffusionXLKDiffusionPipeline,
             )
 
+        try:
+            if not (is_torch_available() and is_transformers_available() and is_sentencepiece_available()):
+                raise OptionalDependencyNotAvailable()
+        except OptionalDependencyNotAvailable:
+            from ..utils.dummy_torch_and_transformers_and_sentencepiece_objects import *
+        else:
+            from .kolors import (
+                KolorsImg2ImgPipeline,
+                KolorsPipeline,
+            )
+
         try:
             if not is_flax_available():
                 raise OptionalDependencyNotAvailable()

diffusers/pipelines/allegro/__init__.py

@@ -0,0 +1,48 @@
+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_allegro"] = ["AllegroPipeline"]
+
+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_allegro import AllegroPipeline
+
+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)