# Stable Diffusion Stable Diffusion is an open source image generation model (text-to-image). It uses diffusion techniques to convert text prompts into images. This model was created by Stability AI. There are multiple versions available, and it continues to evolve. A while ago, the team behind it released Stable Diffusion XL (SDXL), which is much faster than the previous releases. Stability AI continues to work on evolutions and variants, such as [Stable LM](https://stability.ai/stable-lm) for text and code generation, [Stable Fast 3D](https://stability.ai/news/introducing-stable-fast-3d) for generating high-quality 3D assets, [Stable Video 4D](https://stability.ai/news/stable-video-4d) to generate multi-angle videos, [Stable Audio](https://stability.ai/news/stable-audio-open-research-paper), etc. ## Usage Stable Diffusion models are available on different platforms such as [[HuggingFace]]: https://huggingface.co/stabilityai or [[Replicate.com]] ## References - Stable Diffusion - https://stability.ai/news/stable-diffusion-public-release - https://en.wikipedia.org/wiki/Stable_Diffusion - SDXL: https://stablediffusionxl.com/ - Other models: https://stability.ai/stable-image - https://stability.ai/ ## Related - [[AI image generation models]]