Stable Diffusion: Resources

Stable Diffusion Web UI is a free, accessible browser interface powered by Gradio that simplifies interaction with the open-source Stable Diffusion model, offering features like text-to-image generation, image editing, and style customization across platforms.

Stable Diffusion XL or SDXL is the next-generation open weights AI image synthesis model released by Stability AI. It represents a significant advancement in image generation capabilities compared to previous versions of Stable Diffusion, offering higher-resolution imagery and more detailed outputs.

Stable Diffusion ControlNet is a neural network that allows precise control over image generation, enabling features like copying compositions and poses from reference images.

Stable Diffusion 3 is Stability AI's advanced image generation model, boasting enhanced multi-subject prompts, image quality, and spelling. It uses innovative diffusion transformer tech akin to Sora, alongside Flow Matching for multimodal inputs, including video and 3D.

A complete guide to SD3 Medium, including how to download model weights, try the model via API and applications, explore other versions, obtain commercial licenses, and access additional resources and support.

The official release of Stable Diffusion including a CLI, an AI-based Safety Classifier, which detects and suppresses sexualized content, and all the necessary files to get running.

This repository contains Stable Diffusion models trained from scratch and will be continuously updated with new checkpoints. The following list provides an overview of all currently available models. More coming soon.