This workflow turns plain text descriptions into cinematic 1080p video clips with optional synchronized sound using Seedance 2.5. At its core is the ByteDance2TextToVideoNode, which sends your prompt and generation settings (duration, resolution, aspect ratio, FPS, seed) to the Seedance 2.5 backend and returns a finished video stream that can include music, ambience, and simple dialogue aligned to the scene. The SaveVideo node then writes the result to disk as an MP4, preserving the audio track when present.
Technically, you control the visual output by setting width/height (1920x1080 by default) or any custom aspect ratio the model supports, plus a duration cap of up to 30 seconds. The node also exposes a seed so you can iterate with reproducible variations. Because generation is API-based, you get consistent performance without local GPU setup. The simple two-node graph keeps things lean: ByteDance2TextToVideoNode handles synthesis; SaveVideo handles encoding and file naming—ideal for quick iterations, social-ready formats (landscape, square, vertical), and prompt-driven story beats.
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.
