View source for Stable Diffusion

Notes on the different versions of Stable Diffusion from what I can find online.

==Stable Diffusion 1==
Stable diffusion consists of three main components
* CLIP text encoder
* VAE
* UNet latent diffusion model

The main difference between stable diffusion and other diffusion models is that the diffusion operations happens in a low-resolution latent space. For a 512x512 image, the latent may only be 64x64, a factor of 8 times smaller. This significantly reduces the compute resources necessary.

===1.x===

==Stable Diffusion 2==
[https://stability.ai/news/stable-diffusion-v2-release Release Blog Post]

Stable Diffusion 2 replaces the CLIP model with OpenCLIP, a retraining of CLIP using the publicly available LAION-5B dataset with NSFW images removed. By default they generate both 512x512 and 768x768 images.

In additional, SD2 also includes the release of the following:
* Super-resolution model
* Depth to image model
* Inpainting model

===2.1===

==Stable Diffusion XL==
Stable Diffusion XL is a larger model trained on 1024x1024 images.

==Stable Diffusion Turbo==
[https://arxiv.org/abs/2311.17042 paper]

Released Nov 2023, [https://huggingface.co/stabilityai/sd-turbo SD-Turbo] and [https://huggingface.co/stabilityai/sdxl-turbo SDXL-Turbo] are fine-tuned versions of SD2 and SDXL trained using adversarial diffusion distillation (ADD). 

ADD applies fine-tuning using an adversarial loss (from GANs) and a score distillation loss (from DreamFusion) such that each iteration the model produces a complete image. This allows SD-Turbo to produce realistic images in a single iteration while preserving the ability to contine refining the images with additional diffusion iterations.

==Stable Cascade==
[https://stability.ai/news/introducing-stable-cascade Release blog post]
Stable Cascade introduces a latent generator

==Stable Diffusion 3==
Stable Diffusion 3 replaces the diffusion UNet with a [https://arxiv.org/abs/2212.09748 diffusion transformer (DiT)].

==See Also==
* [[Wikipedia: Stable_Diffusion]]