This ComfyUI workflow is designed to facilitate intelligent conversations using OpenAI's advanced language models. By integrating nodes such as OpenAIChatNode and OpenAIChatConfig, this workflow allows users to seamlessly interact with AI for generating text-based responses. The workflow leverages the PreviewAny node to display outputs in real-time, ensuring a smooth interaction process. Additionally, the LoadImage and ImageBatch nodes support the inclusion of visual data, enhancing the context and richness of conversations. This workflow is particularly useful for developers and researchers who need to integrate AI-driven text generation into their applications or projects, providing a robust framework for engaging with OpenAI's API.
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: Chat" (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_chat_api.json");
const asset = client.assets.fromFile("input.png");
wf.setInput("5", "image", asset); // LoadImage
const job = await client.run(wf);
await job.getOutputs("19")[0].toFile("output.png"); // SaveTextThe 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
