This ComfyUI tutorial workflow demonstrates a clean, single-pass approach to upscaling and enhancing portraits using the HitPawGeneralImageEnhance node. You start by importing a low-resolution portrait with LoadImage, route it through HitPawGeneralImageEnhance to increase resolution and restore facial detail, then save the result with SaveImage. For visual QA, the original and enhanced images are fed into ImageCompare for a side-by-side before/after view. A MarkdownNote is included in the graph to provide inline instructions and tips.
Technically, the pipeline is straightforward: LoadImage -> HitPawGeneralImageEnhance -> SaveImage, with a parallel branch to ImageCompare that pairs the original and the enhanced output. The key control is the upscaling factor on HitPawGeneralImageEnhance (e.g., 2x, 3x, 4x). Because the model is tuned for general image enhancement with a portrait emphasis, it tends to recover skin texture and facial features while reducing noise. Note: ImageCompare is part of ComfyUI’s Nodes 2.0 set—if you don’t see it, switch to Nodes 2.0 from the main menu.
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）。
