TextDiffuser-2 Layout Planner

This application focuses on the layout planning aspect of TextDiffuser-2. It allows you to:

Generate text layouts for images based on prompts
Visualize the layout with text positions and bounding boxes
Export the layout information for use in your own HTML5 Canvas UI editor

Based on the paper "TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering" by Jingye Chen et al.

Prompt

Optional Keywords (separated by /)

If provided, the layout planner will try to use these keywords

Width

Height

Temperature

Controls randomness in layout generation. Higher values produce more diverse layouts.

0.1 2

Generate a simple image to provide context (this is just for visualization)

Generate Context Image

Tips for using this demo

The layout planner works best with descriptive prompts
You can specify keywords to ensure they appear in the layout
Increase temperature for more diverse layouts
The context image is optional and just for visualization

Text Layout Visualization

Examples

Prompt	Optional Keywords (separated by /)	Width	Height	Temperature	Generate Context Image

About TextDiffuser-2

TextDiffuser-2 is a system that uses language models for text rendering in images. The layout planner component is responsible for determining where text should be positioned in the generated image.

This demo focuses only on the layout planning aspect, allowing you to generate and export layout information that can be used in your own HTML5 Canvas UI editor.

For the full TextDiffuser-2 implementation, please visit the official repository.