Downloads · 30 days
6
1% of all-time downloads
mespinosami/controlearth-sct
controlearth-sct is a machine learning model from mespinosami. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as apache-2.0.
(Note that this model is for comparison purposes only. A better performing model can be found here.)
Downloads · 30 days
6
1% of all-time downloads
All-time downloads
657
Public
Repo size
1.4 GB
Likes
1
Public
Click a slice to open those files.
.bin1.4 GB · 100%
From the Hugging Face model README
(Note that this model is for comparison purposes only. A better performing model can be found here.)
ControlNet model conditioned on OpenStreetMaps (OSM) to generate the corresponding satellite images.
Trained on the region of Scotland.
To access the better performing model trained on the WorldImagery Clarity dataset, see this model.
The dataset used for the training procedure is the WorldImagery dataset. This dataset is qualitatively worse than its predecessor WorldImagery Clarity dataset.
The code for the dataset construction can be accessed in https://github.com/miquel-espinosa/map-sat.
