This ComfyUI workflow turns plain text into a single, production-ready video clip using the Wan3.0-Video model. At the core is the Wan3ReferenceToVideoApi node, which sends your prompt (and optionally a reference image) to the Wan3.0 text-to-video service and returns a finished clip with synchronized audio. The SaveVideo node then writes the returned clip to disk as a standard video file, giving you a straightforward, single-output pipeline from idea to result.
Technically, the Wan3ReferenceToVideoApi node handles the heavy lifting: it packages your prompt and settings (like duration up to 30 seconds and basic generation controls) and asynchronously retrieves the generated video. If you supply a character or style reference image, the node uses it to enforce visual consistency across the clip—useful for recurring characters or branded subjects. Because the output arrives as a complete video (not per-frame images), you avoid local rendering overhead and retain any audio embedded by the service, while SaveVideo ensures the file is properly saved and easy to share.
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.
