The Face Swap Workflow in ComfyUI is a sophisticated tool designed for visual effects artists who need to perform de-aging or face replacements in video footage. This workflow leverages a combination of AI-driven masking, identity transfer, and inpainting techniques to deliver natural and consistent results across frames. Key nodes such as WanVideoVAELoader and WanVideoModelLoader are used to load and manage video data, while nodes like DrawMaskOnImage and GrowMask help in creating precise masks for face swapping. The workflow also incorporates advanced detection models through OnnxDetectionModelLoader and CLIPVisionLoader to accurately identify and manipulate facial features. By integrating these components, the workflow ensures that the new face blends seamlessly with the original footage, maintaining lighting and performance nuances.
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）。
常見問題
