This ComfyUI tutorial shows how to use the BriaVirtualTryOn node (BRIA model) to dress a person in a photo with one to three product images. You feed one person photo and one or more garment or accessory shots through LoadImage nodes, then the BriaVirtualTryOn node sends them to Bria’s API to generate a realistic worn look. The workflow keeps the person’s face, pose, and background intact while refitting the product to the body. Results return at roughly one megapixel, ready to preview, compare, and export.
Under the hood, BriaVirtualTryOn performs body parsing and pose-aware garment warping, then composites the result with occlusion handling so sleeves, collars, and edges look natural around arms and torso. In this workflow, LoadImage nodes provide the inputs, ImageCompare helps you review before/after, and SaveImage writes the final image to disk. Because this node calls Bria’s cloud service, you’ll need a Bria API key, and your images are processed remotely.
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）。
