This workflow upscales a single input image using the SeedVR2 model to produce a high-definition result with preserved edges and enhanced detail. It’s built around a simple path: LoadImage brings your source into the graph, the SeedVR2 upscaler node (custom node ID c35dd4ba-0fe3-47d6-afce-1c56d9fe5beb) performs super‑resolution, and SaveImage writes the upscaled output to your ComfyUI output directory. An optional ImageCompare node lets you preview a side‑by‑side before/after to verify gains in clarity.
Technically, the SeedVR2 node consumes the input image tensor and applies the SeedVR2 model’s learned upscaling to reconstruct higher‑frequency details at a larger resolution. Because this is deterministic super‑resolution (not text-to-image), results are driven by the source image’s content and quality rather than prompts. The included MarkdownNote inside the graph provides quick, inline guidance. Note that ImageCompare is available only under Nodes 2.0, so enable that mode if you want the built‑in A/B viewer.
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）。
