1.0 KiB
1.0 KiB
Stable Diffusion for Remote Sensing Image Generation
Author: Zhiqiang yuan @ AIRCAS, Send a Email
A simple project for text-to-image remote sensing image generation. We will release the code of using text to control regions for super-large RS image generation later.
Environment configuration
Follow original training repo .
Pretrained weights
We used RSITMD as training data and fine-tuned stable diffusion for 10 epochs with 1 x A100 GPU. When the batchsize is 4, the GPU memory consumption is about 40+ Gb during training, and about 20+ Gb during sampling. The pretrain weights is realesed at last-pruned.ckpt.
Using
Download the pretrain weights to current dir, and run with:
bash sample.sh
We will update the train code ASAP.
Examples
Caption: some boats drived in the sea
