This ComfyUI tutorial walks you through a simple, reliable product-image upscaling pipeline built around three nodes: LoadImage, GeminiImage2Node, and SaveImage. You start by loading your product photo, pass it to GeminiImage2Node configured to use the Nano Banana Pro model, and then save the enhanced result. The Nano Banana Pro model is tuned for product imagery—reinforcing edges, materials, and label regions—so you get cleaner type, crisper contours, and more believable surface detail at a higher resolution.
Technically, GeminiImage2Node serves as an API-backed image-to-image processor. It takes the input from LoadImage, requests an upscaled, detail-enhanced version from the Nano Banana Pro model, and returns a refined output while aiming to maintain color and structure. Because the heavy lifting is done via API, the workflow stays lightweight inside ComfyUI: no local checkpoints to manage, consistent outputs between runs (given the same settings), and straightforward saving through SaveImage to your preferred format and path.
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）。
