This ComfyUI workflow uses the Topaz Bloom 2 model inside the TopazImageEnhanceV2 node to upscale and creatively enhance a single image. Starting with a LoadImage node, your source is passed to Bloom 2 where you control how interpretive the enhancement is using the Creativity slider (1–9). Lower values refine existing detail; higher values allow Bloom 2 to add new textures and visual elements. Optional toggles for Face Recovery and Color Preservation give you fine control over fidelity: recover subtle facial structure without over-smoothing, or lock in original hues to prevent unwanted color shifts. A Grain control can reintroduce texture to avoid a plastic look after upscaling.
For transparency and iteration, the ImageCompare node provides a quick before/after view, making it easy to gauge whether your Creativity level and preservation settings are hitting the mark. When you’re satisfied, SaveImageAdvanced handles export with your preferred file details. The workflow is streamlined—LoadImage → TopazImageEnhanceV2 (Bloom 2) → ImageCompare → SaveImageAdvanced—making it ideal for improving AI artwork and illustrations, adding realism to CG renders, and refining facial detail in generated portraits. If the prompt field in TopazImageEnhanceV2 is left empty, the model will automatically generate one for you, letting you move quickly while still benefiting from stylistic guidance when desired.
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）。
