In this guide, we'll show you how easy it is to launch and run stable diffusion on GPUs with Brev. We've pre-configured a Brev environment for Stable Diffusion so you won't have to do any config at all!
To get started, hit this link to create a new Brev instance
Sign up for an account
It'll redirect you to an instance creation page pre-configured with the defaults you need. (We recommend sticking to the default GPU - it's the cheapest that'll work with Stable Diffusion).
At the bottom, add a payment method...we give you 30 minutes free but we just need to make sure people don't abuse our systems 🙂
Once your instance is created install Brev:
brew install brevdev/homebrew-brev/brev && brev login
Running the model:
Open your new stable-diffusion Brev environment:
brev open stable-diffusion --wait
This will open VSCode inside the Stable Diffusion repo. We've pre-loaded the sd-v1-4 checkpoint in the checkpoints folder. (--wait opens vscode only when the stable diffusion environment is fully loaded this should take about 3 minutes).
To activate your environment run:
conda activate ldm
Now, we're ready-to-go!! In your VSCode terminal, run the command below replacing "Snoop Dogg on Mars" with whichever prompt you want:
python3 scripts/txt2img.py --prompt "Snoop Dogg on Mars" --plms --ckpt checkpoints/sd-v1-4.ckpt --skip_grid --n_samples 1
And boom! Give the model a couple of minutes to load and you should see what your model generated in the outputs folder.
You can open outputs with:
code outputs/txt2img-samples/samples/00000.png code outputs/txt2img-samples/samples/00001.png
Here are some of the outputs we got:
If you thought that was easy, check out our other docs. We've been building the easiest way to do develop on the cloud.