limuloo/MIGC

[CVPR 2024 Highlight] MIGC and [TPAMI 2024] MIGC++ (Official Implementation)

41
/ 100
Emerging

This tool helps creative professionals and marketers generate specific images from text descriptions. You input text prompts along with precise masks or bounding boxes to define where objects should appear. The output is a highly controlled, custom image where multiple elements are accurately placed and consistently rendered, even allowing for iterative edits to refine specific parts of the image.

615 stars. No commits in the last 6 months.

Use this if you need fine-grained control over the placement and attributes of multiple objects in text-to-image generation, such as for scene composition or visual storytelling.

Not ideal if you're looking for a simple, quick text-to-image generator without needing to specify exact object locations or if you lack the technical background to work with image masks and bounding boxes.

digital-art content-creation visual-design marketing-asset-generation animation-production
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

615

Forks

31

Language

Python

License

Last pushed

May 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/limuloo/MIGC"

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