The Flux.1 Inpaint workflow is designed to seamlessly fill in missing or damaged parts of images using the advanced Flux.1 Fill Inpainting model. This workflow leverages the power of the Flux model to intelligently analyze the surrounding context of the missing areas and generate plausible content that blends naturally with the existing image. The process begins with loading an image through the LoadImage node, which is then processed by the inpainting model. The results are saved using the SaveImage node, ensuring that the final output is both high-quality and ready for use. This workflow is particularly useful for restoring old photographs, repairing damaged digital images, or creatively altering images by removing unwanted objects.
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 "Flux.1 图像修复" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("flux_fill_inpaint_example_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("17", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("9")[0].toFile("output.png"); // SaveImageSDK 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）。
常见问题
