This workflow upscales raster illustrations while preserving smooth color regions and clean linework using a Topaz-based enhancement pass. It starts by loading your source image with LoadImage and reading its original dimensions via GetImageSize. A PrimitiveNode controls the scale multiplier (for example, 2x or 4x). ImageScaleBy resizes the image to the target resolution, ensuring predictable output size. The upscaled image is then refined by TopazImageEnhanceV2, which applies learned enhancement tuned for illustrations to smooth gradients, reduce artifacts, and crisp up edges while aiming to preserve color accuracy.
For review and output, ImageCompare (available under Nodes 2.0) places the original and enhanced versions side-by-side so you can quickly judge improvements and spot any artifacts that may appear at aggressive scales. Finally, SaveImage writes the enhanced result to disk. The included MarkdownNote provides inline guidance, and the example input (silent_sanctuary.jpg) helps you test settings before applying the process to your own art. This workflow is practical when you need high-resolution, print- or delivery-ready illustrations from small web images with minimal manual cleanup.
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）。
