ironjr/semantic-draw

Official code for the CVPR 2025 paper "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models."

45
/ 100
Emerging

This project helps graphic designers, digital artists, and content creators rapidly generate complex images by 'painting with concepts.' You provide a blank canvas and define different areas with text prompts (e.g., 'a serene lake,' 'towering mountains'), then watch the image materialize in real-time as you draw. The output is a highly customized, AI-generated image that precisely matches your vision for each region.

587 stars. No commits in the last 6 months.

Use this if you need to quickly prototype or create detailed images where different parts of the scene are controlled by distinct textual descriptions, without unwanted content mixing.

Not ideal if you primarily need to generate single, unsegmented images from a simple text prompt or if you lack access to a dedicated GPU.

digital-art graphic-design content-creation image-generation visual-prototyping
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

587

Forks

53

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ironjr/semantic-draw"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.