This ComfyUI workflow demonstrates creative image upscaling with the Magnific model. Starting from a single input, it produces a high-resolution version at up to 16x enlargement while reconstructing plausible fine details. The core of the graph is the MagnificImageUpscalerCreativeNode, which sends your image and chosen magnification to the Magnific service and returns an upscaled result designed to be both sharp and visually rich.
Technically, the flow is simple and reliable: LoadImage ingests your source file, MagnificImageUpscalerCreativeNode performs the API-based upscale using the Magnific model, ImageCompare lets you review the original and upscaled outputs side-by-side, and SaveImage writes the final image to disk. Because the Magnific upscaler is creatively inclined, it can synthesize detail beyond what’s present in the source while maintaining overall composition, making it useful when conventional interpolation (e.g., bicubic) falls short of producing crisp, print-ready results.
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）。
