OpenAIGPTImageNodeV2 - ComfyUI Built-in Node Documentation

Overview

This node generates images using OpenAI’s GPT Image API. It supports multiple models, allows you to provide input images for editing, and can use a mask to specify which parts of an image to modify.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Text prompt for GPT Image (default: "").	STRING	Yes	N/A
`model`	The OpenAI GPT Image model to use. Selecting a model reveals additional parameters specific to that model.	COMBO	Yes	`"gpt-image-2"` `"gpt-image-1.5"` `"gpt-image-1"`
`model.size`	Image size. Select ‘Custom’ to use the custom width and height (default: “auto”). Only available for `gpt-image-2`.	COMBO	Yes	`"auto"` `"1024x1024"` `"1024x1536"` `"1536x1024"` `"2048x2048"` `"2048x1152"` `"1152x2048"` `"3840x2160"` `"2160x3840"` `"Custom"`
`model.custom_width`	Used only when `size` is ‘Custom’. Must be a multiple of 16 (default: 1024). Only available for `gpt-image-2`.	INT	No	1024 to 3840
`model.custom_height`	Used only when `size` is ‘Custom’. Must be a multiple of 16 (default: 1024). Only available for `gpt-image-2`.	INT	No	1024 to 3840
`model.background`	Return image with or without background (default: “auto”). Only available for `gpt-image-2`.	COMBO	Yes	`"auto"` `"opaque"`
`model.quality`	The quality of the generated image. Only available for `gpt-image-2`.	COMBO	Yes	`"standard"` `"hd"`
`model.images`	Input images for editing. Only available for `gpt-image-2`.	IMAGE	No	N/A
`model.mask`	A mask to specify which parts of the input image to edit. Only available for `gpt-image-2`.	MASK	No	N/A
`n`	How many images to generate (default: 1).	INT	Yes	1 to 8
`seed`	Seed for reproducibility (default: 0). Note: not implemented yet in backend.	INT	Yes	0 to 2147483647

Parameter Constraints and Limitations:

When using gpt-image-2 with a model.size of “Custom”, the custom_width and custom_height must be multiples of 16, the maximum edge must be <= 3840, the aspect ratio must not exceed 3:1, and the total pixel count must be between 655,360 and 8,294,400.
If a mask is provided, an input image (model.images) is required. A mask cannot be used without an input image.
A mask cannot be used with multiple input images.
When a mask is provided, the mask dimensions must match the input image dimensions.
The seed parameter is currently not functional.

Outputs

Output Name	Description	Data Type
`image`	The generated image or images.	IMAGE

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): d0544a2d0f9e9cdd4b121bbf18eb6e43d508b2230e44dfa814649f6a4999e543

​Overview

​Inputs

​Outputs

Overview

Inputs

Outputs