r""" A VAE model with KL loss for encoding images into latents and decoding latent representations into images. This model inherits from [`Mo

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

r""" Pipeline for text-to-image generation using Stable Diffusion. This model inherits from [`DiffusionPipeline`]. Check the superclass docum

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

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

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

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

r""" A 2D UNet model that takes a noisy sample and a timestep and returns a sample shaped output. This model inherits from [`ModelMixin`]. Ch

Args: Context manager to capture `logging` streams logger: 'logging` logger object Returns: The captured output is availa

A 2D Transformer model for image-like data. Parameters: num_attention_heads (`int`, *optional*, defaults to 16): The number of heads

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

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

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

r""" A VQ-VAE model for decoding latent representations. This model inherits from [`ModelMixin`]. Check the superclass documentation for it's

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

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

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

A ControlNet model. Args: in_channels (`int`, defaults to 4): The number of channels in the input sample. flip_s

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

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

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

Norm layer modified to incorporate timestep embeddings.

r""" Pipeline for text-to-audio generation using AudioLDM. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation

Exponential Moving Average of models weights

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

r""" Pipeline for text-to-image generation using Stable Diffusion XL. This model inherits from [`DiffusionPipeline`]. Check the superclass do

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

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

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

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

Output class for KandinskyPriorPipeline. Args: image_embeds (`torch.FloatTensor`) clip image embeddings for text prompt

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

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

Gaussian Fourier embeddings for noise levels.

r""" Processor for implementing the LoRA attention mechanism. Args: hidden_size (`int`, *optional*): The hidden size of t

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

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 valu

Output class for audio pipelines. Args: audios (`np.ndarray`) List of denoised audio samples of a NumPy array of shape `

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

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

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

A Prior Transformer model. Parameters: num_attention_heads (`int`, *optional*, defaults to 32): The number of heads to use for multi

Output class for text to video pipelines. Args: frames (`List[np.ndarray]` or `torch.FloatTensor`) List of denoised fram

The output of [`Transformer2DModel`]. Args: sample (`torch.FloatTensor` of shape `(batch_size, num_channels, height, width)` or `(ba

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

r""" A 1D UNet model that takes a noisy sample and a timestep and returns a sample shaped output. This model inherits from [`ModelMixin`]. Ch

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

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