GPT Image 2.5 Sunburst: Text to Image is a focused ComfyUI template that turns carefully structured prompts into polished, detail-rich images using OpenAI’s image generation API. The core of the workflow is OpenAIGPTImageNodeV2, which packages your prompt (using a "Sunburst" structure that calls out subject, materials, lighting, camera, and composition) and sends it to the selected OpenAI image model. The resulting image stream is then handed to SaveImage, which writes the outputs to your ComfyUI output directory.
Technically, the node exposes common OpenAI image parameters such as model, size/aspect, quality/style, number of outputs, and output format. The Sunburst prompt structure helps preserve subject identity, complex materials, lighting consistency, and scene layout by keeping a stable "anchor" block in your prompt across iterations. You iterate by adjusting only the variable parts (e.g., pose, background, or mood) while leaving the anchor descriptors unchanged—yielding high-fidelity refinements without rebuilding the entire scene each time.
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 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");The 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
