OpenAIGPTImageSVGNode - ComfyUI Built-in Node Documentation - ComfyUI

Overview

OpenAI GPT Image 2.6 SVG generates an editable SVG from a prompt with OpenAI’s GPT Image models. The result is vector markup, so shapes and text stay editable in a vector editor. Two models are available: gpt-image-2.6-flare and gpt-image-2.6-sunburst.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
`model`	The GPT Image model to use for the SVG.	DYNAMIC_COMBO	Yes	`"gpt-image-2.6-flare"` `"gpt-image-2.6-sunburst"`

gpt-image-2.6-flare and gpt-image-2.6-sunburst Inputs

Both models share the same parameters.

Parameter	Description	Data Type	Required	Range
`model.prompt`	Description of the SVG to draw. (default: `""`)	STRING	Yes	N/A
`model.size`	Size of the reference image the SVG is drawn from. (default: `"1024x1024"`)	COMBO	Yes	`"1024x1024"` `"1024x1536"` `"1536x1024"`
`model.background`	Background of the reference image. (default: `"auto"`)	COMBO	Yes	`"auto"` `"opaque"` `"transparent"`
`model.quality`	Quality of the reference image the SVG is drawn from. (default: `"low"`)	COMBO	Yes	`"low"` `"medium"` `"high"` `"xhigh"` `"max"`
`model.complexity`	How much the model plans the reference image before rendering. (default: `"high"`)	COMBO	Yes	`"low"` `"medium"` `"high"`
`model.seed`	Controls whether the node re-runs; results are non-deterministic regardless of seed. (default: `42`)	INT	Yes	0 to 2147483647

Outputs

Output Name	Description	Data Type
`svg`	The generated vector image as SVG markup.	SVG

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): 8ac2f473b265d3b6857e6280a1c017301b124fc6d671ec83a59c677218062c90