This ComfyUI workflow turns a single text prompt into a finished video clip using the Flux 3 model. The Flux3TextToVideoNode interprets natural language into a complete moving scene with coherent action, camera motion, and synchronized sound. It’s designed for quick turnarounds: you set the prompt, pick a duration between 5–20 seconds, choose an aspect ratio from 9:16 to 21:9, and the node generates a 720p, 24 fps result with built-in audio.
Technically, the pipeline is minimal and focused. Flux3TextToVideoNode handles end-to-end generation from text, returning the video content (and its audio track) at the requested length, frame rate, and aspect ratio. The SaveVideo node then writes the output to disk as a single playable file. With only two nodes, it’s easy to understand, fast to set up, and reliable for creating social-ready clips, ad mockups, and cinematic concept shots without extra reference images or complex settings.
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.
FAQ
