> For the complete documentation index, see [llms.txt](https://stablediffusion.gitbook.io/overview/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://stablediffusion.gitbook.io/overview/stable-diffusion-overview/technology/architecture.md).

# Architecture

Stable Diffusion uses a kind of diffusion model (DM), called a latent diffusion model (LDM).\[1] Introduced in 2015, diffusion models are trained with the objective of removing successive applications of Gaussian noise on training images which can be thought of as a sequence of denoising autoencoders. 

<figure><img src="https://66508924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJaRV9HsOrKmAQxWrp4OQ%2Fuploads%2Fwylsdf7LxzwyPxal9TMP%2FStable_Diffusion_architecture.png?alt=media&amp;token=54a170d9-beb7-43ea-a70e-a8b1e443b726" alt=""><figcaption><p>Diagram of the latent diffusion architecture used by Stable Diffusion</p></figcaption></figure>

Stable Diffusion consists of 3 parts: the variational autoencoder (VAE), U-Net, and an optional text encoder.\[11] The VAE encoder compresses the image from pixel space to a smaller dimensional latent space, capturing a more fundamental semantic meaning of the image.\[12] Gaussian noise is iteratively applied to the compressed latent representation during forward diffusion.\[11] The U-Net block, composed of a ResNet backbone, denoises the output from forward diffusion backwards to obtain a latent representation.&#x20;

Finally, the VAE decoder generates the final image by converting the representation back into pixel space.\[11] The denoising step can be flexibly conditioned on a string of text, an image, or another modality. The encoded conditioning data is exposed to denoising U-Nets via a cross-attention mechanism.\[11] For conditioning on text, the fixed, pretrained CLIP ViT-L/14 text encoder is used to transform text prompts to an embedding space.\[1] Researchers point to increased computational efficiency for training and generation as an advantage of LDMs.\[13]\[14]