yuval-alaluf/Attend-and-Excite

Official Implementation for "Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models" (SIGGRAPH 2023)

43
/ 100
Emerging

This project helps artists, designers, and marketers who use AI to generate images from text descriptions. It improves the reliability of image generation by ensuring all key elements and their specific attributes from a text prompt (e.g., 'a red car and a blue bike') appear correctly in the final image. You input your desired text prompt and get back a more accurate, high-quality image that faithfully represents every detail you asked for.

767 stars. No commits in the last 6 months.

Use this if you are generating images from text prompts and find that the AI frequently omits specific objects or incorrectly applies attributes (like colors) to the wrong subjects.

Not ideal if your image generation needs are basic and don't require precise control over multiple objects or their exact attributes within a single prompt.

AI-art-generation digital-content-creation visual-design creative-asset-production text-to-image
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

767

Forks

64

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yuval-alaluf/Attend-and-Excite"

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