BuildJsonPromptIdeogram - ComfyUI Built-in Node Documentation

This node constructs a structured JSON prompt specifically formatted for the Ideogram 4 image generation model. It organizes your text instructions, style preferences, and color palette into the required JSON structure that the model expects.

Inputs

Parameter	Description	Data Type	Required	Range
`element`	Prompt elements from the node Create Bounding Boxes.	ARRAY	Yes	-
`high_level_description`	Optional description of the image in one or two sentences. Strongly recommended. (default: empty)	STRING	No	-
`background`	Mandatory description of the image background or environment. (default: empty)	STRING	Yes	-
`style`	The visual style category for the generated image. (default: “none”)	COMBO	Yes	`"none"` `"photo"` `"art_style"`
`photo`	Camera or lens details for photographic outputs (e.g. 35mm, f/1.4, bokeh). Only available when style is set to “photo”. (default: empty)	STRING	No	-
`art_style`	Art style description (e.g. flat vector illustration, bold outlines). Only available when style is set to “art_style”. (default: empty)	STRING	No	-
`aesthetics`	Mandatory aesthetic keywords (e.g. moody, cinematic, desaturated). (default: empty)	STRING	Yes	-
`lighting`	Mandatory lighting description (e.g. golden hour, rim light, dramatic shadows). (default: empty)	STRING	Yes	-
`medium`	Mandatory medium type (e.g. photograph, illustration, 3d_render, painting, graphic_design). When style = photo, set to photograph. (default: empty)	STRING	Yes	-
`color_palette`	Hex color codes that steer the image’s dominant colors. Up to 16 entries.	COLORS	No	-

Note: When the style parameter is set to “photo”, the photo input becomes available and you should set the medium parameter to “photograph”. When style is set to “art_style”, the art_style input becomes available.

Outputs

Output Name	Description	Data Type
`prompt`	A structured JSON dictionary containing the high-level description, style description (if applicable), and compositional deconstruction with background and elements.	DICT

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): 56a045e0c7c19531e6443696c0bdf3946df066d03eea7d2d217b7d92f052592f

​Inputs

​Outputs

Inputs

Outputs