Open-source image and video generation
Interfaces for running open image and video models on your own hardware: node graphs for full control, canvases for editing, and form-based tools that work on modest GPUs. The software is open source; each model you download carries its own licence.
The GPL-3.0 node-graph engine for image, video, audio and 3D generation that supports the newest open models, from Stable Diffusion and Flux to Wan and LTX video, on NVIDIA, AMD, Intel and Apple hardware, offline.
An Apache-2.0 creative image tool with a unified canvas for inpainting and outpainting, node workflows, and support for 28 model families from Stable Diffusion to Flux and Qwen Image, run as a local web app.
An Apache-2.0 all-in-one web interface for AI image and video generation, descended from AUTOMATIC1111's WebUI, with LoRA, ControlNet, quantisation that cuts video memory up to four times, and the widest hardware list here.
An MIT image and video generation web interface, formerly StableSwarmUI, with a simple Generate tab for beginners and a raw ComfyUI workflow tab for experts, that can spread work across several GPUs.
Questions people ask
What is the best open-source alternative to Midjourney?
ComfyUI (GPL-3.0) for the widest model support and full control through a node graph, including video. InvokeAI (Apache-2.0) for a canvas with inpainting and outpainting. SD.Next (Apache-2.0) for unusual or low-memory hardware. SwarmUI (MIT) for a simple tab now and ComfyUI's graph later.
Do I need an expensive GPU?
Not necessarily. SD.Next lists AMD, Intel, Apple and DirectX GPUs and CPU-only use, with quantisation its README says cuts video memory up to four times. ComfyUI runs on NVIDIA, AMD, Intel, Apple Silicon and Ascend. Larger models still want more memory, and none of the READMEs states a minimum.
Are the image models open source too?
Separate question, and often no. The interfaces here are open source, but each model you download has its own licence, and some restrict commercial use. SwarmUI's README says it plainly: any models used have their own licences. Check the model card before selling what you make.
Can these generate video?
Yes, several. ComfyUI lists Wan, LTX-Video, HunyuanVideo, CogVideoX and Mochi; SwarmUI lists MiniMax H3, Wan and LTX-2; SD.Next covers text to video and image to video. InvokeAI lists one video model, Wan, as API only.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.