SD.Next

Open source

Open-source server and web interface for generating, captioning and processing AI images and video with Stable Diffusion and other diffusion models.

vladmandic.github.io
SD.Next homepage screenshot
GitHub stars
7.4k
Last 30 days
+25(+0%)
Last commit
2 days ago
Repository age
3 years
Licence
Apache-2.0
Self-hosted
Yes

About SD.Next

SD.Next is an open-source server application with a web interface for AI image and video generation. It is built on Stable Diffusion and works with a long list of diffusion models, so one install covers text-to-image, image-to-image, text-to-video and image-to-video, along with editing steps such as inpainting, outpainting and detailer passes.

Models can be picked from a list of reference models and are fetched automatically, or you can add your own files and the interface detects them. Guidance options include LoRA, ControlNet and IPAdapters, and the processing side covers captioning, tagging, upscaling, interpolation, colorizing and filtering. Custom scripts and extensions add further workflows.

Memory use gets particular attention: a quantization engine called SDNQ and a balanced offload mode between CPU and GPU memory aim to let larger models run on limited hardware. The project lists support for NVIDIA, AMD and Intel Arc GPUs, Apple M1/M2, OpenVINO and CPU-only runs, plus Docker recipes and a built-in installer that handles updates.

Key features

  • Automatic download of reference models
  • SDNQ quantization to cut VRAM use
  • Balanced offload between CPU and GPU memory
  • Captioning and tagging with built-in LLM, VLM and tagger models
  • Interface translated into about 15 languages with themes
  • Built-in installer with automatic updates

Good fit for

  • Text-to-image and image-to-image generation
  • Text-to-video and image-to-video generation
  • Inpainting and outpainting
  • Captioning and tagging image sets
  • Upscaling and colour-correcting images
Built with
Python tools
Tags
stable diffusion
image generation
video generation
webui
ai art
open source

SD.Next: questions and answers

What is SD.Next used for?
SD.Next is an open-source server and web interface for generating, captioning and processing AI images and video with Stable Diffusion and other diffusion models. It is a good fit for text-to-image and image-to-image generation, text-to-video and image-to-video generation, and inpainting and outpainting.
Is SD.Next open source?
Yes. SD.Next is open source under the Apache-2.0 licence. Its source code is on GitHub at vladmandic/sdnext and is written mainly in Python.
Is SD.Next free?
Yes. SD.Next is open source, so the software itself is free to use.
Can I self-host SD.Next?
Yes. SD.Next can be self-hosted on your own server or infrastructure.
What is SD.Next an alternative to?
SD.Next is an open-source alternative to Midjourney, Leonardo.Ai, Runway and Pika. Other open-source alternatives to Midjourney include ComfyUI, Open Generative AI and InvokeAI.
Is SD.Next actively maintained?
Yes. The most recent commit to SD.Next was on 11 November 2026. The project has 7.4k stars on GitHub, with 25 added in the last 30 days.

Open-source alternatives to SD.Next

See all

SaaS alternatives to SD.Next

See all