This ComfyUI tutorial walks you through a compact text-to-video pipeline powered by the Wan3.0-Video model. The core of the workflow is the Wan3ReferenceToVideoApi node, which sends your prompt (and optional reference images) to the Wan3.0-Video service, then returns a single rendered clip. The SaveVideo node writes that clip to disk. You’ll control duration (up to 30 seconds), resolution/aspect, frame rate, seed, and other generation settings directly on the API node, making it easy to iterate from a single graph.
Technically, Wan3ReferenceToVideoApi handles the remote job lifecycle: it packages your text prompt and any reference inputs, submits the request, polls until completion, and outputs a finished video. The “Reference” capability helps maintain strong character or style consistency when you supply a face or character image. If your API plan/model supports it, the node can also return synchronized sound; otherwise you’ll receive a silent video you can score later. SaveVideo finalizes the output with your chosen filename pattern and fps, giving you a simple, reliable path from text to production-ready footage.
API
Use this workflow from code
Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.
Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.
// Install (beta)
npm i @comfyorg/sdk
// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).
Comfy Cloud API access requires a plan with an API key.
