OpenAIGPTImage1 - ComfyUI Built-in Node Documentation

Generates images synchronously through OpenAI’s GPT Image endpoint.

Generates images synchronously through OpenAI’s GPT Image endpoint. It can create new images from a text prompt or edit existing images when an input image and optional mask are provided. The node supports the gpt-image-1, gpt-image-1.5, and gpt-image-2 models and is marked as deprecated.

Inputs

Parameter	Description	Data Type	Required	Range
prompt	Text prompt for GPT Image (default: "")	STRING	Yes	-
seed	Random seed for generation; not implemented yet in backend (default: 0)	INT	No	0 to 2147483647
quality	Image quality, affects cost and generation time (default: “low”)	COMBO	No	”low" "medium" "high”
background	Return image with or without background (default: “auto”)	COMBO	No	”auto" "opaque" "transparent”
size	Image size. Select “Custom” to use the custom width and height (GPT Image 2 only) (default: “auto”)	COMBO	No	”auto" "1024x1024" "1024x1536" "1536x1024" "2048x2048" "2048x1152" "1152x2048" "3840x2160" "2160x3840" "Custom”
n	How many images to generate (default: 1)	INT	No	1 to 8
image	Optional reference image for image editing	IMAGE	No	-
mask	Optional mask for inpainting (white areas will be replaced)	MASK	No	-
model	GPT Image model to use (default: “gpt-image-2”)	COMBO	No	”gpt-image-1" "gpt-image-1.5" "gpt-image-2”
custom_width	Used only when size is “Custom”. Must be a multiple of 16 (GPT Image 2 only) (default: 1024)	INT	No	1024 to 3840, step 16
custom_height	Used only when size is “Custom”. Must be a multiple of 16 (GPT Image 2 only) (default: 1024)	INT	No	1024 to 3840, step 16

Parameter Constraints:

• When image is provided, the node uses the image editing endpoint.
• mask can only be used when image is provided.
• When using mask, only single images are supported (batch size must be 1).
• mask and image must be the same size.
• Custom resolution (size = “Custom”) is only supported by the gpt-image-2 model.
• Custom width and height must be multiples of 16.
• The longest edge of a custom resolution must be 3840 or less.
• Custom resolution aspect ratio must not exceed 3:1.
• Custom resolution total pixels must be between 655,360 and 8,294,400.
• The gpt-image-1 and gpt-image-1.5 models only support the sizes auto, 1024x1024, 1024x1536, and 1536x1024. Other sizes are only supported by the gpt-image-2 model.

Outputs

Output Name	Description	Data Type
IMAGE	Generated or edited image(s). Multiple images are returned as a batch; if returned images have different dimensions, they are resized to match the first image.	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): f0f0db7fd2cdf8efd2155522b289aa8f3f939fa79a6e9060b0ffbb2dd20efa1e