Text to Image
This document explains the Text to Image node, which generates an image from a text prompt using an AI model.
Node Description
The Text to Image node generates image(s) from a text instructions using an AI model. The AI Model is Imagen 3.
Imagen 3 is a Google AI model, capable of generating images with even better detail, richer lighting and fewer distracting artifacts.
Node Inputs
Required Fields
Instructions:
Detailed instructions specifying the image to generate.
Example: "A beautiful sunset over a calm ocean with a clear sky."
Node AI Settings
Number of Images:
The number of images to generate.
You can generate up to 4 images at a time.
Example: 1
Acceptable values: 1
, 2
, 3
, 4
Water Mark:
Whether to add a digital water mark to the generated image.
The water mark is invisible to the human eye.
Default: true
Aspect Ratio:
The aspect ratio of the generated image.
Acceptable values:
1:1 (1024px x 1024px)
16:9 (1408px x 768px)
4:3 (1280px x 896px)
3:4 (896px x 1280px)
9:16 (768px x 1408px)
Default: 16:9
Node Output
Output:
The generated images.