#139 · Primary category： Image Generation
rich-text-to-image
Rich-Text-to-Image Generation
Project last updated：10/09/23
GitHub Stars
801
Forks
70
Contributors
3
License
MIT
Why we included this project
Anyone who has wrestled with a long Stable Diffusion prompt, trying to push one concept up and another down, will appreciate the lever this project offers. Instead of rewriting the whole prompt, you format the text itself: font size, color, style, and footnotes become controls for the generation, letting you reweight tokens explicitly, pin down exact colors, and steer local style. The code runs on Stable Diffusion v1-5 and SD-XL, and the HuggingFace demo plus an A1111 WebUI extension make it easy to try without being a researcher. It grew out of an ICCV 2023 paper from UMD, Adobe, and CMU, and for teams already working in the Stable Diffusion ecosystem it is a useful reference for how formatting metadata can drive diffusion conditioning.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.