The StreamDiffusionTD operator wraps StreamDiffusion as a TouchDesigner node for diffusion-based real-time visuals inside a TD network

The StreamDiffusionTD operator (by DotSimulate / Lyell Hintz) is a TouchDesigner .tox component that integrates StreamDiffusion into the TD node graph. Rather than running StreamDiffusion as a separate process and piping frames in and out, the operator exposes diffusion generation as a TOP (Texture Operator) node: it accepts texture input (a camera feed or rendered scene) and outputs a diffusion-processed texture, so the result composites into the normal TD signal chain. Setup requires installing StreamDiffusion and its Python dependencies into TD’s Python environment, importing the StreamDiffusionTD .tox, and configuring prompt/seed/model settings as node parameters. Licensing note: the StreamDiffusion engine is open source (MIT), but the StreamDiffusionTD .tox is distributed to supporters via the author’s Patreon, even though this Derivative tutorial itself is free to view.

Examples

In TD: Camera TOP -> StreamDiffusionTD TOP (prompt ‘impressionist painting’) -> Out TOP. The camera feed is processed in real time through the diffusion model and the stylized output is rendered. The prompt is a live-editable string parameter on the node.

Assessment

Describe the signal path from a camera input to a diffusion-processed output in a TD network using StreamDiffusionTD. Then identify the licensing distinction between StreamDiffusion (the engine) and StreamDiffusionTD (the TD operator) and explain its practical implication for a ‘free’ project.