USE CASE

Run Stable Diffusion on an RTX 4090 in the cloud

Generate images with Stable Diffusion WebUI Forge on a 24 GB GPU. No hardware to buy, pay per second.

See RTX 4090 machines Checking live prices…

Billed per second from your USD balance. Stop or terminate the machine when you are done.

Recommended GPU

RTX 4090 · RTX 5090

SDXL and Flux need 16–24 GB of VRAM. An RTX 4090 or RTX 5090 renders a 1024 px image in seconds.

PyTorch

NVIDIA CUDA + PyTorch development environment, ready with SSH and Jupyter.

1
Rent the machine
Open the catalog with RTX 4090 and the PyTorch template already selected and press Rent.
See RTX 4090 machines
2
Connect with SSH
Copy the SSH command from your machine's page and add the port forward for the web interface.
```
$ ssh -p <PORT> root@<HOST> -L 7860:localhost:7860
```
The SSH command is on your machine's page. The -L part forwards the port so the app opens in your own browser.

Run these commands once. The first start downloads the model and takes a few minutes.

$ git clone https://github.com/lllyasviel/stable-diffusion-webui-forge
cd stable-diffusion-webui-forge
./webui.sh -f --listen --port 7860

4
Open it in your browser
Go to http://localhost:7860 on your computer. Terminate the machine when you are done to stop all charges.

Can I use my own models and LoRAs?

Yes. Download them into the models folder on the machine with wget or upload them with scp.

What happens to my images when I stop?

Stopping keeps the disk and its files; disk storage is still charged. Terminating deletes everything, so download your images first.