This ComfyUI workflow leverages the OpenAI GPT-Image-1 model to perform inpainting on images, allowing users to edit and enhance visuals by filling in missing or undesired parts. The workflow integrates several nodes, including the OpenAIGPTImage1 node for processing the image through the API, LoadImage for importing the image to be edited, and SaveImage for exporting the final result. The MarkdownNote node is included to provide users with detailed instructions or notes within the workflow itself. This setup is particularly useful for tasks that require precise image editing, such as restoring old photographs or removing unwanted objects from a scene. By utilizing the GPT-Image-1 model, the workflow ensures high-quality inpainting results that are both contextually aware and visually coherent.
API
Use this workflow from code
Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.
Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.
// Install (beta)
npm i @comfyorg/sdk
// Run "OpenAI: GPT-Image-1 Inpaint" (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("api_openai_image_1_inpaint_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("29", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("28")[0].toFile("output.png"); // SaveImageThe SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).
Comfy Cloud API access requires a plan with an API key.
FAQ
