OpenAIDalle2 - ComfyUI Built-in Node Documentation

Generates images synchronously via OpenAI’s DALL·E 2 endpoint.

How It Works

This node connects to OpenAI’s DALL·E 2 API to create images based on text descriptions. When you provide a text prompt, the node sends it to OpenAI’s servers which generate corresponding images and return them to ComfyUI. The node can operate in two modes: standard image generation using just a text prompt, or image editing mode when both an image and mask are provided. In editing mode, it uses the mask to determine which parts of the original image should be modified while keeping other areas unchanged.

Inputs

Parameter	Description	Data Type	Required	Range
`prompt`	Text prompt for DALL·E (default: empty)	STRING	Yes	-
`seed`	not implemented yet in backend (default: 0)	INT	No	0 to 2147483647
`size`	Image size (default: “1024x1024”)	COMBO	No	”256x256" "512x512" "1024x1024”
`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	-

Note: Image editing mode is activated only when both image and mask are provided together. If only one of them is supplied, an error is raised. The mask must be the same size as the image; otherwise an error is raised. In editing mode, the white areas of the mask indicate the regions that will be replaced.

Outputs

Output Name	Description	Data Type
`IMAGE`	The generated or edited image(s) from DALL·E 2	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): c6bba5dd44ebed1d795e6ec93bdd2e19685e8ae9f24be9145ad9d74d3a9b7a0c

​How It Works

​Inputs

​Outputs

How It Works

Inputs

Outputs