33 lines
1.3 KiB
Markdown
33 lines
1.3 KiB
Markdown
# Stable Diffusion for Remote Sensing Image Generation
|
|
|
|
#### Author: Zhiqiang yuan @ AIR CAS, [Send a Email](yuan_zhi_qiang@sina.cn)
|
|
|
|
A simple project for text-to-image remote sensing image generation,
|
|
and we will release the code of `using text to control regions for super-large RS image generation` later.
|
|
Also welcome to see the project of [image-condition fake sample generation](https://github.com/xiaoyuan1996/Controllable-Fake-Sample-Generation-for-RS) in [TGRS, 2023](https://ieeexplore.ieee.org/abstract/document/10105619/).
|
|
|
|
## Environment configuration
|
|
|
|
Follow [original training repo](https://github.com/justinpinkney/stable-diffusion.git) .
|
|
|
|
|
|
## Pretrained weights
|
|
|
|
We used [RSITMD](https://github.com/xiaoyuan1996/AMFMN) 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](https://github.com/xiaoyuan1996/AMFMN).
|
|
|
|
## Using
|
|
Download the pretrain weights to current dir, and run with:
|
|
```commandline
|
|
bash sample.sh
|
|
```
|
|
We will update the train code ASAP.
|
|
|
|
## Examples
|
|
**Caption:** Some boats drived in the sea.
|
|
|
|
|
|
**Caption:** A lot of cars parked in the airport.
|
|
|