Upscale:使用 Nano Banana Pro 進行 AI 圖像增強 - After
Upscale:使用 Nano Banana Pro 進行 AI 圖像增強 - Before

The 'Nano Banana Pro: AI Image Enhancement' workflow is designed to upscale and enhance AI-generated images, transforming them into high-resolution 4K outputs with improved sharpness and coherence. This workflow leverages the power of the Nano Banana Pro model, known for its exceptional ability to refine image details and enhance visual quality. The process begins with the LoadImage node, which allows users to upload their AI-generated images into the system. The core of the enhancement process is handled by the GeminiImage2Node, which applies sophisticated algorithms to upscale and enhance the image. Finally, the SaveImage node ensures that the enhanced image is saved in the desired format and location.

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。

utility_nanobanana_pro_ai_image_fix.json
正在取得工作流 JSON…

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 "Upscale:使用 Nano Banana Pro 進行 AI 圖像增強" (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("utility_nanobanana_pro_ai_image_fix_api.json");

const asset = client.assets.fromFile("input.png");
wf.setInput("2", "image", asset); // LoadImage

const job = await client.run(wf);
await job.getOutputs("5")[0].toFile("output.png"); // SaveImage

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)。

Comfy Cloud API 存取需有 API 金鑰的方案。

常見問題

常見問題

查看所有工作流
Showing 30 of 30 templates