tsunghan-wu/SLD

🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)

36
/ 100
Emerging

This project helps graphic designers, content creators, or marketers refine AI-generated images to precisely match textual descriptions. You input an image and a text prompt (either for a new image or editing an existing one), and it outputs a corrected, higher-quality image that aligns better with your instructions. This is ideal for anyone who uses AI tools like DALL-E or Stable Diffusion but struggles with the generated images not quite matching their vision.

187 stars. No commits in the last 6 months.

Use this if you need to generate new images or edit existing ones with fine-grained control over details like object count, spatial relationships, or specific attributes, and your current AI image generator isn't precise enough.

Not ideal if you're looking for a simple, out-of-the-box consumer application for quick, unrefined image generation or editing without needing high precision.

AI image generation digital art content creation graphic design image editing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

187

Forks

10

Language

Python

License

MIT

Last pushed

Apr 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tsunghan-wu/SLD"

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