OpenAI just dropped GPT-Image 1, the model behind ChatGPT-4o’s image generation, now available via API — and ComfyUI already supports it with new API Nodes (Beta)! Here’s how it works 👇

🎨 Features: • Prompt GPT-Image-1 directly in ComfyUI using text or image inputs • Set resolution and quality • Supports image editing + transparent backgrounds • Seamlessly mix with local workflows like WAN 2.1, FLUX Tools, and more

🧪 How to use it: • Update your ComfyUI. Double-click and search for “OpenAI GPT Image 1” Node • Log in, add credits, and you're good to go!

💡 Example use case You can combine GPT-Image-1 output with local nodes like WAN 2.1 video generation, upscale, or style transfer — all in ComfyUI.

🖌️ Of course, you can bring your favorite Ghibli images into a video in a single workflow

🧾 Billing is prepaid — you only pay the OpenAI API cost + a transaction fee. Access is opt-in, for those who want to tap into external SOTA models right inside ComfyUI. And don’t worry — ComfyUI will always be free and open source!

For more details, check out our blog at:

Automate up to 70% of your customer support today. Save time and help your users find answers quickly. Try now at

@OpenAI 你们的速度是真快🫡

@OpenAI This is awesome!!