Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

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

Overview

This node generates images from text descriptions using the Luma UNI-1 model. It takes a text prompt and optional settings like aspect ratio and style, then sends the request to the Luma API to create an image.

Inputs

ParameterData TypeRequiredRangeDescription
promptSTRINGYes1–6000 charactersText description of the desired image.
modelCOMBOYes"uni-1"
"uni-1-max"
Model to use for generation. Selecting a model reveals additional settings for that model.
seedINTYes0 to 2147483647Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0)

Model-specific Inputs

When "uni-1" or "uni-1-max" is selected for the model parameter, the following inputs become available:
ParameterData TypeRequiredRangeDescription
aspect_ratioCOMBOYes"auto"
"3:1"
"2:1"
"16:9"
"3:2"
"1:1"
"2:3"
"9:16"
"1:2"
"1:3"
Output image aspect ratio. "auto" lets the model pick based on the prompt. (default: "auto")
styleCOMBOYes"auto"
"manga"
The visual style for the generated image. (default: "auto")
web_searchBOOLEANYesTrue / FalseWhether to allow the model to search the web for additional context. (default: False)
image_refIMAGENoUp to 9 imagesReference images to guide the generation.
Note on style and aspect_ratio constraints: If style is set to "manga", the aspect_ratio must be either "auto" or one of the following portrait ratios: "2:3", "9:16", "1:2", "1:3". Using a landscape or square ratio with "manga" style will cause an error.

Outputs

Output NameData TypeDescription
imageIMAGEThe generated image as a tensor.

Source fingerprint (SHA-256): cd680f8b9e6bcf5fa415aa2d9ec3126bf8873d14bd6f4cd127491cfa242e5548