This ComfyUI tutorial workflow demonstrates Wan3.0’s reference-to-video generation: starting from two images, it produces a lifelike, up-to-30-second video that preserves character identity and visual style. Two LoadImage nodes bring in your references (for example, a clean subject image and a context/pose or style image). These feed directly into the Wan3ReferenceToVideoApi node, which sends the request to the Wan3.0 service and returns a ready-to-save video. A SaveVideo node then writes the final clip to disk as an MP4.
Technically, the pipeline is lean and reliable: the heavy lifting happens remotely via the Wan3ReferenceToVideoApi node, so your local GPU is not a bottleneck. The MarkdownNote node in the graph includes inline tips and reminders about inputs and expected outputs. Because the generator is reference-driven, the quality and composition of your two images strongly influence identity lock, motion coherence, and background fidelity. Use this when you want consistent character animation from stills, quick scene mocks from storyboards, or product visuals derived from brand imagery.
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.
