SD.Next is an all-in-one, actively developed WebUI for AI image and video generation, built on the Diffusers library and supporting a huge range of modern generative models. It has around 7,400 stars on GitHub and is updated continuously — the latest commits landed in October 2026.
Where the classic Stable Diffusion WebUI grew around a single model family, SD.Next was rebuilt around Hugging Face Diffusers so it can run many architectures from one interface: Stable Diffusion 1.5 and SDXL, SD3, Flux, and numerous other image and video models, with new models typically supported soon after release. The interface covers text-to-image and image-to-image generation, inpainting, upscaling, captioning and image processing, backed by an efficient pipeline with modern samplers, schedulers and GPU memory optimizations. It runs locally on Windows, Linux and macOS, installs with a single script, and includes both a streamlined UI for everyday generation and deep settings for power users. SD.Next is free and open source under the Apache-2.0 license.
SD.Next is completely free and open source under the Apache-2.0 license. You download it from GitHub, run it on your own hardware, and use your own models — no subscriptions or per-image fees.
SD.Next is for AI artists, hobbyists and developers who generate images and video locally and want a single, up-to-date interface that keeps pace with the newest open models instead of being locked to one generation of Stable Diffusion.