RubenGres/Seg2Sat
Using StableDiffusion and ControlNet to generate synthetic aerial images
This tool helps urban planners, game developers, and environmental analysts generate realistic or stylized aerial images from simple land cover segmentation maps. You provide a map outlining areas like buildings, water, or forests, along with a text description, and it produces a high-resolution, photorealistic aerial photograph. This is perfect for creating new datasets or visuals where actual aerial imagery isn't available.
Use this if you need to quickly generate diverse aerial views based on basic land-use planning data or for visual assets in simulations and games.
Not ideal if you require highly precise, georeferenced satellite imagery for official surveying or critical infrastructure planning.
Stars
94
Forks
5
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RubenGres/Seg2Sat"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neggles/animatediff-cli
a CLI utility/library for AnimateDiff stable diffusion generation
sakalond/StableGen
Transform your 3D texturing workflow with the power of generative AI, directly within Blender!
victordibia/peacasso
UI interface for experimenting with multimodal (text, image) models (stable diffusion).
ai-forever/Kandinsky-2
Kandinsky 2 — multilingual text2image latent diffusion model
carefree0910/carefree-drawboard
🎨 Infinite Drawboard in Python