r""" A Resnet block. Parameters: in_channels (`int`): The number of channels in the input. out_channels (`int`, *optiona

An error indicating that an optional dependency of Diffusers was not found in the environment.

Image Processor for VAE Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to downscale the image's

Output class for image pipelines. Args: images (`List[PIL.Image.Image]` or `np.ndarray`) List of denoised PIL image

Output class for Stable Diffusion pipelines. Args: images (`List[PIL.Image.Image]` or `np.ndarray`) List of denoise

r""" A cross attention layer. Parameters: query_dim (`int`): The number of channels in the query. cross_attention_dim (`

Base class for the scheduler's step function output. Args: prev_sample (`torch.FloatTensor` of shape `(batch_size, num_channels,

Transformer block for image-like data. First, project the input (aka embedding) and reshape to b, t, d. Then apply standard trans

Flax implementation of 2D Resnet Block. Args: in_channels (`int`): Input channels out_channels (`int`):

A residual block that can optionally change the number of channels. :param channels: the number of input channels. :param emb_channels

Transformer model for image-like data. Takes either discrete (classes of vector embeddings) or continuous (actual embeddings) inputs.

A residual block that can optionally change the number of channels. :param channels: the number of input channels. :param emb_channels

A sequential module that passes timestep embeddings to the children that support it as an extra input.

A sequential module that passes timestep embeddings to the children that support it as an extra input.

A 2D downsampling layer with an optional convolution. Parameters: channels (`int`): number of channels in the inputs and

A 2D upsampling layer with an optional convolution. Parameters: channels (`int`): number of channels in the inputs and ou

r""" Default processor for performing attention-related computations.

Dual transformer wrapper that combines two `Transformer2DModel`s for mixed inference. Parameters: num_attention_heads (`int`, *o

Norm layer modified to incorporate timestep embeddings.

Output of decoding method. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)`):

Args: Output class for Stable Diffusion pipelines. images (`List[PIL.Image.Image]` or `np.ndarray`) List of denoised

Temporal convolutional layer that can be used for video (sequence of images) input Code mostly copied from: https://github.com/modelscope/m

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. ht

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. ht

r""" Processor for performing attention-related computations with extra learnable key and value matrices for the text encoder.

A 1D downsampling layer with an optional convolution. Parameters: channels (`int`): number of channels in the inputs and

Subclass torch's LayerNorm to handle fp16.

多特征融合 AFF

GroupNorm layer modified to incorporate timestep embeddings.

r""" Processor for performing scaled dot-product attention (enabled by default if you're using PyTorch 2.0), with extra learnable key and va

Output class for audio pipelines. Args: audios (`np.ndarray`) List of denoised samples of shape `(batch_size, num_c

r""" A basic Transformer block. Parameters: dim (`int`): The number of channels in the input and output. num_attention_h

直接相加 DirectAddFuse

A downsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determ

A downsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determ

Output class for Stable Diffusion pipelines. Args: images (`np.ndarray`) Array of shape `(batch_siz

Gaussian Fourier embeddings for noise levels.

Masked Autoencoder with VisionTransformer backbone

Implementation of the GELU activation function currently in Google BERT repo (identical to OpenAI GPT). Also see the Gaussian Error Linear

Spatially conditioned normalization as defined in https://arxiv.org/abs/2209.09002

Transformer model for video-like data. Parameters: num_attention_heads (`int`, *optional*, defaults to 16): The number of heads

Vision Transformer with support for global average pooling

多特征融合 iAFF

r""" Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).

Computes and stores the average and current value

Computes and stores the average and current value

r""" Processor for implementing attention for the Custom Diffusion method. Args: train_kv (`bool`, defaults to `True`):

r""" A feed-forward layer. Parameters: dim (`int`): The number of channels in the input. dim_out (`int`, *optional*): Th

Flax implementation of 2D Downsample layer Args: in_channels (`int`): Input channels dtype (:obj:`jnp.dtyp

r""" A Spatial Transformer layer with Gated Linear Unit (GLU) activation function as described in: https://arxiv.org/pdf/1506.02025.pdf

Flax implementation of 2D Upsample layer Args: in_channels (`int`): Input channels dtype (:obj:`jnp.dtype`

r"""HTSAT based on the Swin Transformer Args: spec_size (int | tuple(int)): Input Spectrogram size. Default 256 patch_size (int

r""" Multiple `ControlNetModel` wrapper class for Multi-ControlNet This module is a wrapper for multiple instances of the `ControlNetModel

A modified Snake function which uses separate parameters for the magnitude of the periodic components Shape: - Input: (B, C, T)

Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` or `(batch size, num_vector_embeds - 1, num_late

An upsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determi

An upsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determi

Output class for Alt Diffusion pipelines. Args: images (`List[PIL.Image.Image]` or `np.ndarray`) List of denoised P