SD.Next
An open-source, all-in-one WebUI for AI image and video generation, captioning and processing, built on Stable Diffusion and supporting dozens of models.
SD.Next is an open-source server application and web interface for AI image and video generation, built on Stable Diffusion and supporting dozens of advanced diffusion models, letting a user create, refine, caption, upscale and process images and videos in one cross-platform application.
It automatically downloads a selected reference model, or detects and adds a user's own models, and includes SDNQ, a quantization engine that runs pre-quantized models or quantizes on the fly for up to a fourfold reduction in VRAM with little or no quality or performance impact. A "Balanced Offload" feature dynamically balances CPU and GPU memory to run larger models on limited hardware, and captioning and enhancement draw on more than 25 built-in LLM and vision-language models, OpenCLIP models, and taggers such as WaifuDiffusion and DeepDanbooru.
It supports text-to-image, image-to-image, text-to-video and image-to-video generation, editing workflows such as detailing, hi-res refine, inpainting and outpainting, guidance tools such as LoRA and ControlNet, is localized into about 15 languages with multiple UI themes, offers desktop and mobile interfaces, and installs with an automatic-update installer.