Skip to main content
OpenAI GPT-Image-1 Node Screenshot OpenAI GPT-Image-1 is part of the ComfyUI Partner nodes series that allows users to generate images through OpenAI’s GPT-Image-1 model. This is the same model used for image generation in ChatGPT 4o. The OpenAI GPT-Image-1 node synchronously generates images through OpenAI’s image generation API. It receives text prompts and returns images matching the description. GPT-Image-1 is OpenAI’s most advanced image generation model currently available, capable of creating highly detailed and realistic images.

​
What GPT-Image-1 is good at

  • Text-to-image generation
  • Image editing functionality (inpainting through masks)
  • Image-to-image generation from a reference image
  • Multiple image input, batching several reference images into a single generation

​
Example outputs

Text-to-image generation from a single text prompt: ComfyUI openai-gpt-image-1 workflow Image-to-image generation from a reference image: ComfyUI openai-gpt-image-1 workflow Multiple image input, combining several reference images into one generation: Multiple Image Input Example Inpainting, replacing a masked area of an input image: ComfyUI openai-gpt-image-1 workflow

​
Use it in ComfyUI

GPT-Image-1 workflows

Run the text-to-image, image-to-image, multiple image input, and inpainting workflows in ComfyUI, locally or on Comfy Cloud