The Vidu Q3 Audio-Visual Video Generation workflow is designed to create short, dynamic videos ranging from 1 to 16 seconds, complete with synchronized audio and seamless scene transitions. Utilizing the Vidu and Vidu Q3 models, this workflow allows users to either input a text prompt or upload an image as the starting point for video creation. The core of this workflow is the Vidu3TextToVideoNode, which processes the input to generate a cohesive video sequence. This node is particularly powerful as it combines both visual and auditory elements, ensuring that the audio is perfectly aligned with the video content. The SaveVideo node then captures the generated output, allowing users to easily save and share their creations. This workflow is particularly useful for content creators looking to quickly generate engaging multimedia content without the need for extensive video editing skills.
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 "Vidu Q3 視聽影片產生" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("api_vidu_q3_text_to_video_api.json");
const job = await client.run(wf);
await job.getOutputs("8")[0].toFile("output.png"); // SaveVideoSDK 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）。
常見問題
