Rich-Text-to-Image for Stable Diffusion WebUI

September 26, 2023 ยท View on GitHub

Project Page | Paper | Code | HuggingFace Demo | Video

The WebUI extension for integrating a rich-text editor for text-to-image generation.

image

This extension is for AUTOMATIC1111's Stable Diffusion web UI, allows the Web UI to add rich-text-to-image to the original Stable Diffusion model to generate images.

Installation

  1. Open "Extensions" tab.
  2. Open "Install from URL" tab in the tab.
  3. Enter URL of this repo (https://github.com/songweige/sd-webui-rich-text) to "URL for extension's git repository".
  4. Press "Install" button.
  5. Restart Web UI.

Usage

The extension now supports SD-v1.5 (default), SD-XL-v1.0, and ANIMAGINE-XL. The checkpoints will be automatically downloaded when the model is first selected.

Font Color

color

Font color is used to control the precise color of the generated objects.

Footnote

footnote

Footnotes provide supplementary descriptions for selected text elements.

Font Style

style

Just as the font style distinguishes the styles of individual text elements, it is used to define the artistic style of specific areas in the generation.

Font Size

size

Font size indicates the weight of each token in the final generation.

Acknowledgement

The extension is built on the extension-templates. The rich-text editor is built on Quill. The model code is built on huggingface / diffusers.