Verified project record

vladmandic/sdnext

A unified, cross-platform server and web interface built on Stable Diffusion for generative image and video creation, captioning, and processing. Users can operate across Windows, Linux, and macOS with automatic model downloads and optional GPU hardware.

Project overview

Project type: Model Runtime · Image & Vision · Video
Use cases: Image Processing
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Creators and researchers seeking an all-in-one web application for Stable Diffusion workflows without a mandatory coding requirement.

Key capabilities

Supports workflows including Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video, Inpainting, Outpainting, and custom scripts.
Users can select a reference model from a list and it will be automatically downloaded and ready to use; added models are automatically detected.
State-of-the-Art model quantization engine allowing pre-quantized models or on-the-fly quantization for up to 4x VRAM reduction.
Dynamically balances CPU and GPU memory to allow running larger models on limited hardware.
Caption and enhance images using 25+ built-in LLM and VLM models, OpenCLiP models, and Tagger with WaifuDiffusion and DeepDanbooru models.
Full image correction color-grading suite of tools for processing generated or input images.
Cross-platform web application with platform-specific auto-detection and tuning, localized to approximately 15 languages with UI themes, featuring both desktop and mobile interfaces.
Built-in installer with automatic updates and dependency management.

Limitations and risks

Telemetry, data boundaries, and cost dependencies are not documented in the available information.
The system requires diffusion models for image and video generation, which must be automatically downloaded or manually added.

Getting started

Setup is rated as easy due to a built-in installer with automatic updates and dependency management. Users can clone the repository, navigate into the directory, and run the webui.sh shell script to start the web UI.

Evidence and sources

GitHub project description: SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
README: SD.Next is a state-of-the-art, open-source server application and web interface (WebUI) for AI image and video generation, built on Stable Diffusion and supporting dozens of advan…
README: SD.Next is feature-rich open-source AI art generation platform with a focus on performance, flexibility, and user experience.
README: Automatic model download: simply select a model from the list of reference models and it will be downloaded and ready to use Or download and add your own models and they will be a…
README: - **Desktop** and **mobile** interfaces - Built in **installer** with automatic updates and dependency management

Reviewed at: 2026-07-18T07:07:23Z