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
Utiliser ce workflow depuis le code
Chaque workflow Comfy est un graphe JSON. Le contenu ci-dessous est ce workflow, exactement comme ComfyUI l’exécute — récupérez-le depuis l’URL, gardez-le dans le contrôle de version, ou chargez-le dans ComfyUI et exécutez-le nœud par nœud.
Exécutez-le depuis TypeScript ou Python avec le Comfy SDK. Le même code cible Comfy Cloud ou un ComfyUI auto-hébergé — seule l’URL de base change.
// 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");Le SDK prend un workflow au format API : ouvrez ce workflow dans ComfyUI et utilisez Fichier → Exporter le workflow (API).
L’accès à l’API Comfy Cloud nécessite un forfait avec clé API.
