Chen-Yang-Liu/Text2Earth

[IEEE GRSM 2025 🔥] "Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model"

41
/ 100
Emerging

Text2Earth helps remote sensing professionals generate synthetic satellite and aerial imagery based on descriptive text. You provide a text description, like "Seven green circular farmlands," and it creates a corresponding image. This tool is for geospatial analysts, urban planners, and environmental scientists who need to visualize specific land features or scenarios without real-world photography.

165 stars.

Use this if you need to quickly generate specific remote sensing images from text descriptions, or modify existing images by describing changes to be made.

Not ideal if you require extremely high-fidelity, real-world accuracy for critical applications or if you lack programming experience.

remote-sensing geospatial-analysis urban-planning environmental-modeling satellite-imagery
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

165

Forks

8

Language

Python

License

Apache-2.0

Category

gan-based-t2i

Last pushed

Jan 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Chen-Yang-Liu/Text2Earth"

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