This ComfyUI tutorial workflow uses PixverseV6TextToVideoNode to turn text prompts into distribution-ready video clips, then saves the result with SaveVideo. PixVerse V6 runs generation via API, so you don’t need a local GPU to produce smooth motion. You can target up to 15 seconds at 1080p, choose common aspect ratios (16:9, 9:16, 1:1), and optionally include integrated audio if enabled in the node. The node handles the request/response with the PixVerse V6 service and returns an encoded video that SaveVideo writes to disk.
What makes this setup especially useful is multi-shot scene direction in a single pass. You can outline a short narrative as a sequence of labeled scenes within your prompt so the model maintains continuity across cuts (character, setting, lighting) without juggling multiple runs. The result is a fast way to prototype social clips, product teasers, and story snippets that are already framed correctly for your target platform.
API
從程式碼使用此工作流
每個 Comfy 工作流都是一個 JSON 圖。下方的 payload 就是此工作流，與 ComfyUI 執行時完全相同 — 你可以從此 URL 取得、放入版本控制，或在 ComfyUI 載入並逐節點執行。
使用 Comfy SDK 以 TypeScript 或 Python 執行。相同程式碼可用於 Comfy Cloud 或你自架的 ComfyUI — 只需更改 base URL。
// 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");SDK 需使用 API 格式的工作流：請在 ComfyUI 開啟此工作流，並使用 檔案 → 匯出工作流（API）。
