ComfyUI
A node graph for image and video models. Steeper to learn than anything else here, and the only one that lets you build exactly the pipeline you want.
- Self-hosted
- Allowed
The old workhorse. Small, fast, endlessly fine-tuned, and still the model most community checkpoints are built on.
Superseded on quality by everything after it, and still the reason a six-year-old graphics card is enough to start. Its size is its advantage: 512×512 output, about 4 GB of VRAM, and a decade of community checkpoints and LoRAs that only exist for this architecture.
The licence is a RAIL licence, not a plain open-source one: it carries use restrictions. Read it before you build a business on it.
A node graph for image and video models. Steeper to learn than anything else here, and the only one that lets you build exactly the pipeline you want.
The original web interface for Stable Diffusion, by AUTOMATIC1111. Enormously extended, widely copied, and no longer moving quickly.
Motion added to an existing image model. The technique that made short animated clips possible on a home graphics card.
The image model hub: checkpoints, LoRAs and the example images that show what they actually do. Indispensable, and volatile.
Image generation as a native Mac and iPhone app. Free, local, and startlingly good at running large models on Apple silicon.
A polished, professional-feeling image studio with a unified canvas. The one to show someone who bounced off the others.
Generation built into a real painting program. You paint, it fills in; you paint over it, it adjusts.
Another descendant of the AUTOMATIC1111 interface, aimed at breadth: many model families, and AMD and Intel GPUs as first-class targets.
A fork of AUTOMATIC1111's interface, reworked underneath for speed and lower memory use. The same screen, faster, on less VRAM.