Stable Diffusion: Open-Source Image Generation

Stable Diffusion is the most widely used open-source text-to-image model family. It powers countless community tools and workflows for creative image generation, customization, and local/private deployment.

Features

Text-to-Image and Image-to-Image

Generate images from prompts, or transform and enhance existing images.

SDXL and Variants

Modern SDXL/SDXL Turbo models improve quality and speed; rich ecosystem of checkpoints and LoRAs.

Full Local Control

Run on local GPUs or servers for privacy and customization.

Rich Tooling Ecosystem

Popular UIs like Automatic1111 and ComfyUI; extensive community nodes and workflows.

Best For

Artists and designers who want full control
Teams needing on-prem or private deployments
Power users building custom pipelines and styles

Notes

See also ai-tools/Stability AI.md for the company and platform behind Stable Diffusion.

Last built with the static site tool.