Dsh Comfyui Canvas
wbin0001/dsh-comfyui-canvas · skills
The agent writes prompts and edits nodes right in chat, applies them live to the canvas you're watching, and turns ideas into images, video, and 3D — all without switching front-en.
★ 7GitHub stars
0Forks
2026-09-08Last updated
JavaScriptLanguage
MITLicense
Key features
- From chat to canvas to artwork — drive ComfyUI as a visual workflow IDE inside DSH.
- By default the bridge is unauthenticated, matching ComfyUI's own /prompt trust model — anyone who can reach the ComfyUI port can read the canvas, report state, and dispatch commands (load_workflow/run consume GPU).
- comfyui_reload currently supports Windows only (uses netstat/taskkill)
- Embed ComfyUI (local or cloud) as a split-screen canvas in DeepSeek Harness Web: the agent sparks ideas, writes prompts and scripts right in the chat, applies them live to the canvas in front of you, and produces images, music, video, and 3D.
- From idea to finished output without ever leaving the conversation or switching front-ends
Requirements
- ComfyUI running (local by default at 127.0.0.1:8188
- for a cloud instance, deploy the bridge node there and make sure DSH can reach it) with the bridge node installed
Install command
dsh plugin --profile web add github:wbin0001/dsh-comfyui-canvas