wbin0001/dsh-comfyui-canvas

中文 · English

Embed your ComfyUI (local or cloud) as a split-screen canvas tab inside DeepSeek Harness Web, and merge DSH's LLM power with ComfyUI's generation into one visual creation platform — 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:

• Canvas ops — compose and arrange pipelines, read/write workflows, edit nodes, wire links, run, tune parameters, and debug errors, all live and WYSIWYG on the exact canvas you are looking at
• Production tasks — batch parameter sweeps (batch_run) and automatic output-image retrieval back into the chat (get_outputs), powering multi-modal creative and batch generation across images, music, video, and 3D
• Environment upkeep — one-click launch of ComfyUI and one-click upgrade of the core plus every custom node (upgrade), keeping the stack healthy without interruption

This package is the DSH-side plugin, and it ships the ComfyUI-side bridge node too. For headless/scale workloads it can be paired with the official ComfyUI MCP server — see Canvas vs MCP.

What you get

Surface	Description
ComfyUI canvas tab	A ComfyUI conversation view that embeds the ComfyUI frontend (local or cloud) side by side with the Chat rail. The iframe stays alive across tab switches (no reload).
Visual canvas copilot	The agent operates the canvas you are looking at — nodes appear, links wire, widgets change and runs trigger live on screen, so you watch every step instead of trusting an opaque JSON edit. Output images come back into the chat via comfyui_get_outputs.
Canvas ops tools	comfyui_read_workflow, add_node, connect, set_param, remove_node, inject_text, load_workflow, run, debug — build and fix workflows on the live canvas; inject_text writes conversation text straight into a node or a new wirable source.
Production tools	comfyui_batch_run sweeps a parameter matrix (seeds/prompts/strengths) in one go; comfyui_get_outputs pulls the resulting images back into the chat; comfyui_attach_image uploads a local image into ComfyUI's input/ for a LoadImage node; comfyui_export_api exports the live canvas as API-format workflow JSON for comfy-cli headless batch runs.
Upkeep tool	comfyui_upgrade one-click updates the ComfyUI core and every git-backed custom node; comfyui_config reports the active connection and canvas focus.
Canvas focus mode	The agent can tell (via comfyui_config) whether the browser is on the canvas tab for the current session, and focus on canvas work only then. Session-isolated.
Settings page	ComfyUI base URL / port / network mode / bridge token / launch command / rail width. Changes apply live. Customized nav icon with ComfyUI logo.
Rail polish	Image previews inside the input box, a + button to attach local images (DSH's official attachment path), approval popup over the canvas (split layout), send button pinned to the panel corner.

Install

1. Install the DSH plugin

dsh plugin add github:<your-name>/dsh-comfyui-canvas

or from a local checkout:

# in your DSH profile
pnpm add <path-to-this-package>

The bundled cordis.patch.yml mounts the plugin automatically (dsh.bundle.patch).

2. Install the ComfyUI bridge node

The agent tools talk to the ComfyUI page through a bridge (/dsh-bridge/*). The bridge node ships inside this repo at comfyui-bridge/ComfyUI-DSH-Canvas — copy it into ComfyUI's custom_nodes:

Windows (PowerShell / cmd):

# from this repo checkout:
Copy-Item -Recurse comfyui-bridge\ComfyUI-DSH-Canvas <ComfyUI>\custom_nodes\ComfyUI-DSH-Canvas

macOS / Linux (bash):

# from this repo checkout:
cp -r comfyui-bridge/ComfyUI-DSH-Canvas <ComfyUI>/custom_nodes/ComfyUI-DSH-Canvas

Or, after dsh plugin add, the installed package carries it too:

# Windows (PowerShell)
Copy-Item -Recurse (npm root -g)\dsh-comfyui-canvas\comfyui-bridge\ComfyUI-DSH-Canvas <ComfyUI>\custom_nodes\ComfyUI-DSH-Canvas

# macOS / Linux
cp -r $(npm root -g)/dsh-comfyui-canvas/comfyui-bridge/ComfyUI-DSH-Canvas <ComfyUI>/custom_nodes/ComfyUI-DSH-Canvas

Then restart ComfyUI and load the canvas page once (the injected bridge.js reports the graph and listens for commands).

3. Configure

Open Settings → ComfyUI 画布 and set the ComfyUI base URL (default http://127.0.0.1:8188), port, network mode, optional bridge token, launch command, and the right-side rail width.

The launch command differs by platform:

Platform	Example
Windows	ComfyUI启动器.bat (or python main.py)
macOS	python main.py or ./start.sh
Linux	python main.py or ./start.sh

Security

The bridge (/dsh-bridge/*) is the only network surface this plugin adds to ComfyUI. Read this before exposing ComfyUI beyond loopback.

• Trust model. 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). Commands are whitelisted on the frontend, so no arbitrary code execution is possible, but the surface is real.
• Bind to loopback. Keep ComfyUI on 127.0.0.1 unless you explicitly need LAN/cloud access. networkMode is informational; the actual bind is whatever ComfyUI was launched with (--listen).
• Optional shared token. Set a token in Settings → ComfyUI 画布 → 桥接 Token AND launch ComfyUI with the same value in its own environment (DSH_BRIDGE_TOKEN=...). When the token is set, every agent-initiated request — reading the canvas, dispatching a command, polling its result — must present Authorization: Bearer <token>; the host side sends it automatically and the bridge rejects requests without it. The frontend's own status reporting (/report, result callbacks) stays open, since the injected page cannot hold the token; those endpoints only mutate the in-memory snapshot and never dispatch execution. Leave it empty on both sides for the default open behavior.
• Multiple tabs are safe. Commands are targeted at the last-reporting frontend (clientId), so several open ComfyUI tabs do not each execute a command.

Platform support

Works on Windows, macOS and Linux. The agent tools talk to ComfyUI over plain HTTP (/dsh-bridge/*), so nothing platform-specific lives in the plugin itself — only the copy command and the ComfyUI launch command differ, and both are documented above.

Usage

1. Open a conversation, switch to the ComfyUI tab — the canvas splits on the left, chat on the right.
2. Ask the agent to do canvas work: "读取当前工作流", "给 KSampler 设 seed 为 42", "检查画布有没有报错", "运行一次".
3. The agent reads comfyui_config first, so it knows it's on the canvas and stays focused on canvas operations.

Conversation → canvas

Content the agent generates in the chat — images and text — can become ComfyUI workflow node inputs directly, closing the loop from conversation idea to canvas output:

• comfyui_attach_image: upload a local image into ComfyUI's input/ and optionally point a LoadImage node at it. Uses ComfyUI's native /upload/image (not the bridge) — the host reads and uploads the file from the agent's own machine, which matters when the DSH machine and the ComfyUI machine differ (cloud deployments).
• comfyui_inject_text: write text to a node's widget; or create a new source node, set its value, and connect it to a target input — "conversation text as a wirable source". A one-step wrapper over add_node + set_param + connect; set_param alone suffices when only an existing widget changes, and inject_text is for "create a new source and wire it".
• comfyui_export_api: export the live canvas as API-format workflow JSON (the format /prompt and comfy-cli run_workflow consume), bridging canvas → MCP headless runs.

Architecture boundary: file transfer (image → input/) goes through the host + native API; canvas node ops go through bridge commands; reading results goes through native /history + /view — three layers that never mix.

Canvas vs MCP — two ways to drive ComfyUI

This plugin is the canvas driver: it sees and edits the live canvas the user is looking at (add nodes, wire links, tweak widgets, run, fetch the run's output images via comfyui_get_outputs, sweep parameters via comfyui_batch_run). It never needs a saved workflow file.

For pipeline-style / headless workloads, ComfyUI's official Comfy CLI (comfy-cli) is a complementary tool. It is a standalone Python CLI (installed via pip install comfy-cli, and can also expose an MCP server) — not a DSH plugin, so it is used separately from this plugin rather than mounted into the DSH profile. It covers capabilities this canvas plugin deliberately does not re-implement:

Capability	This plugin (canvas)	ComfyUI CLI (comfy-cli)
Operate the live canvas the user sees	✅	—
Run a saved / API-format workflow file	✅ (via canvas)	✅ (directly)
Batch-queue runs + fetch output images	✅ (batch_run + get_outputs)	✅ (run_workflow + fetch_outputs)
Official workflow templates	—	✅ (templates)
Model download / management	—	✅ (models)
Hosted/paid models (Flux, Veo, …)	—	✅ (partner)
Pre-flight graph validation (validate / deps)	✅ (debug, local)	✅ (validate, server)

Recommended split: use this plugin while you are building/tuning a workflow on the canvas; use the Comfy CLI once you want to run the same graph headlessly at scale (batch pipelines, templates, model management, hosted models). They talk to the same ComfyUI instance and can be used side by side. Install the Comfy CLI with:

pip install comfy-cli   # standalone CLI, not a DSH plugin — see https://github.com/Comfy-Org/comfy-cli

Requirements

• DeepSeek Harness Web (DSH), Node ^22.19.0 || >=24
• 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
• A browser tab with the ComfyUI page open (the canvas tab loads it automatically)

Development

npm run check   # node --check both lib files

The plugin lives in the DSH profile under node_modules/dsh-comfyui-canvas; edit lib/index.js (host tools) and lib/client.js (web client), then restart DSH.

Repository layout

dsh-comfyui-canvas/
├── cordis.patch.yml          # DSH bundle layer (auto-mount)
├── comfyui-bridge/           # ComfyUI-side bridge node (self-contained)
│   └── ComfyUI-DSH-Canvas/
│       ├── __init__.py       # /dsh-bridge/* HTTP routes on the ComfyUI server
│       └── entry/bridge.js   # injected frontend: reports graph + runs commands
├── lib/
│   ├── index.js              # DSH host: 15 canvas tools + session-isolated mode
│   └── client.js             # DSH web: canvas tab / settings / rail polish
├── LICENSE
├── README.md
└── package.json

The bridge is the only ComfyUI-side dependency. It exposes /dsh-bridge/workflow|report|command|result and is injected into the ComfyUI page via app.registerExtension; without it the agent tools cannot reach the canvas.

Known issues

(None pending. The former "node previews missing after a run" is fixed in v0.1.1: removed the iframe's referrerpolicy="no-referrer" to match the native tab environment, and bridge.js now listens to ComfyUI's executed event to force a canvas redraw.)

License

MIT