This workflow uses Muse Image 1.0 to edit an image with natural-language instructions while preserving the rest of the scene. Two LoadImage nodes supply inputs: one is the primary image you want to edit, and the second is a visual reference that guides the look (style, color palette, material cues) of the edit. The MetaMuseImageEditApi node sends both images plus your instruction to the hosted Muse Image 1.0 service and returns a single edited image. SaveImageAdvanced then writes the result to disk with your chosen filename and subfolder.
Technically, the graph is simple and reliable: LoadImage → MetaMuseImageEditApi → SaveImageAdvanced, with a MarkdownNote included to summarize usage. The API node interprets your instruction (e.g., "make the house red while keeping the desert sky unchanged") and applies targeted changes while maintaining scene layout and context. Example inputs included with the template—deep_blue_whale_swim_scene.png and desert_red_modern_house.png—let you try style- or color-guided edits immediately.
API
通过代码使用此工作流
每个 Comfy 工作流都是一个 JSON 图。下面的内容就是此工作流的完整数据，ComfyUI 运行时也是如此——你可以从该 URL 获取、放入版本控制，或在 ComfyUI 中加载并逐节点运行。
使用 Comfy SDK 从 TypeScript 或 Python 运行。相同代码可用于 Comfy Cloud 或你自托管的 ComfyUI——只需更改基础 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 需要 API 格式的工作流：在 ComfyUI 中打开此工作流，使用 文件 → 导出工作流（API）。
