Norm layer modified to incorporate timestep embeddings.

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

r""" copy from diffuser 0.11.1 A cross attention layer. Parameters: query_dim (`int`): The number of channels in the query.

Norm layer modified to incorporate timestep embeddings.

Output of AutoencoderKL encoding method. Args: latent_dist (`DiagonalGaussianDistribution`): Encoded outputs of `Encoder` represented as the

r""" copy from diffuser 0.11.1 A cross attention layer. Parameters: query_dim (`int`): The number of channels in the query.

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

r""" copy from diffuser 0.11.1 A cross attention layer. Parameters: query_dim (`int`): The number of channels in the query.

Uses the CLIP transformer encoder for text (from Hugging Face)

Uses the CLIP transformer encoder for text (from Hugging Face)

Embeds text prompt into vector representations. Also handles text dropout for classifier-free guidance.

Embeds text prompt into vector representations. Also handles text dropout for classifier-free guidance.

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

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

The approximate form of Gaussian Error Linear Unit (GELU) For more details, see section 2: https://arxiv.org/abs/1606.08415

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

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

Uses the CLIP transformer encoder for text (from Hugging Face)

r""" A variant of the gated linear unit activation function from https://arxiv.org/abs/2002.05202. Parameters: dim_in (`int`): The nu

r""" GELU activation function

Utilities for training and sampling diffusion models. Original ported from this codebase: https://github.com/hojonathanho/diffusion/bl

Utilities for training and sampling diffusion models. Original ported from this codebase: https://github.com/hojonathanho/diffusion/bl

A diffusion process which can skip steps in a base diffusion process. :param use_timesteps: a collection (sequence or set) of timesteps from

A diffusion process which can skip steps in a base diffusion process. :param use_timesteps: a collection (sequence or set) of timesteps from

Embeds text prompt into vector representations. Also handles text dropout for classifier-free guidance.

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

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

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