Local LLM
comfyui-mcp
Agent-native control plane for ComfyUI — generate media in plain chat.
★ 785 starsMIT
View guide →// ai-3d · JiSenHua/ComfyUI-TD
ComfyUI-TD
ComfyUI-TD is an open-source ai 3d project by JiSenHua (JiSenHua/ComfyUI-TD on GitHub). It has 167 GitHub stars and 8 forks, is released under the AGPL-3.0 license, and was last updated on GitHub on 20 August 2026.
Stream ComfyUI output live into TouchDesigner.
💎 Hidden gem★ 167 stars⑂ 8 forksAGPL-3.0updated 2026-08
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- JiSenHua/ComfyUI-TD
- GitHub stars
- 167
- Forks
- 8
- License
- AGPL-3.0
- Last updated on GitHub
- 20 August 2026
- Category
- AI 3D
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- GitHub
// how it works
How it works
- Install ComfyUI
Set up your ComfyUI instance.
- Add the nodes
Install ComfyUI-TD into custom_nodes.
- Open TouchDesigner
Prepare a receiving network.
- Stream live
Pipe AI output into your visuals.
// features
Why people love it
Real-time streaming
Live pipe from ComfyUI to TD.
Five media types
Images, video, 3D, audio, text.
Custom nodes
Drops into ComfyUI workflows.
TouchDesigner native
Built for live visual work.
Generative visuals
AI imagery on stage.
AGPL-3.0
Open source, share-alike.
Advertisement
// run it
Run it yourself
- Step 1 — Clone into custom_nodes
Download it into your ComfyUI nodes folder.
cd ComfyUI/custom_nodes git clone https://github.com/JiSenHua/ComfyUI-TD.git - Step 2 — Install requirements
Add the Python dependencies.
cd ComfyUI-TD && pip install -r requirements.txt - Step 3 — Restart ComfyUI
Relaunch to load the bridge nodes.
# restart ComfyUI, then wire the TD nodes
// use cases
What you can build
- Drive live visuals with generative AI.
- Stream ComfyUI video into TouchDesigner.
- Build AI-powered installations.
- VJ with real-time AI imagery.
Advertisement
// faq
Questions, answered
What is ComfyUI-TD?
Custom nodes streaming ComfyUI output live into TouchDesigner, at JiSenHua/ComfyUI-TD.
What can it stream?
Images, video, 3D models, audio, and text.
Do I need TouchDesigner?
Yes, for the receiving end of the stream.
Is it free?
The source is open under AGPL-3.0.
Who is it for?
VJs, installation artists, and live-visual performers.
// keep exploring
Similar tools
Video
ComfyUI VideoHelperSuite
Nodes related to video workflows
★ 1.9k starsGPL-3.0
View guide →Image
ComfyUI-ArchAi3d-Qwen
Professional AI interior-design toolkit for ComfyUI.
★ 71 starsNOASSERTION
View guide →AI 3D
GSOPs
Gaussian splatting operators that bring 3DGS into SideFX Houdini.
★ 627 starsAGPL-3.0
View guide →AI 3D
three.ws
Turn text or a photo into a living 3D avatar with an LLM brain and wallet.
★ 221 starsApache-2.0
View guide →AI 3D
img2threejs
Turn a reference image into a procedural, animation-ready Three.js model - as code
★ 17.7k starsApache-2.0
View guide →// alternatives
Alternatives in AI 3D
The most-starred other AI 3D projects in the LibreAI catalogue — the realistic shortlist if ComfyUI-TD is not the right fit.
- mcp-for-blender★ 30.2k
Control Blender with natural language: an MCP plugin that lets any LLM model, light and animate in 3D
- editor★ 24.7k
Pascal Editor: an open-source 3D architectural editor with MCP tools for humans and AI agents
- text-to-cad★ 18.4k
Give your AI agent CAD superpowers - generate real STEP/STL models from text
- img2threejs★ 17.7k
Turn a reference image into a procedural, animation-ready Three.js model - as code
- Hunyuan3D-2★ 15.0k
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
// more in ai-3d
More in AI 3D
Nearby AI 3D projects in the catalogue, closest in stars to ComfyUI-TD — keep exploring the shelf either side of it.
- OpenPointClass★ 202
Free, fast semantic segmentation of 3D point clouds.
- 360Extractor★ 154
High-performance desktop application for 360° video preprocessing.
- openreality★ 214
Turn phone video into 3D scenes your AI agent can query.
- cadgenbench★ 138
The benchmark for measuring AI-driven CAD generation and editing.
- bambu-studio-ai★ 216
Agent skill that takes 3D printing from model search to printed part.
- claude-image-generation★ 99
Agent skills connecting Claude to image gen — from free 3D to Cloudflare diffusion.
Get ComfyUI-TD
Free and open — grab the source, star the repo, and start creating.