🧬 Automatic1111
Jarvislabs Automatic 1111
instance helps you with setting up a UI to interact with Stable Diffusion. It is based on Automatic1111 repository.
We are not the creators of it 😊, we are just making it easier to use with Jarvislabs GPU instances. If you are stuck somewhere, we will try our best to help. You can always ping us using the chat.
Create a Automatic 1111 instance
Start a instance with framework as Automatic 1111.
Download weights
You need to put the model weights under /home/stable-diffusion-webui/models/Stable-diffusion
.
For example to get started with SD1.5 you can follow the below steps from /home
directory.
wget https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt
mv v1-5-pruned-emaonly.ckpt /home/stable-diffusion-webui/models/Stable-diffusion/
You can download different versions of SD model weights.
For SD 2.1 - 768:
Weights : wget https://huggingface.co/stabilityai/stable-diffusion-2-1/resolve/main/v2-1_768-ema-pruned.ckpt
Config : wget https://raw.githubusercontent.com/Stability-AI/stablediffusion/main/configs/stable-diffusion/v2-inference-v.yaml
For SD 2.1 - 512:
Weights : wget https://huggingface.co/stabilityai/stable-diffusion-2-base/blob/main/512-base-ema.ckpt
Config : wget https://raw.githubusercontent.com/Stability-AI/stablediffusion/main/configs/stable-diffusion/v2-inference-v.yaml
You need to rename the yaml file to the same name of weights that you wish to use.
You can learn more how to use the UI from the official wiki page.
Launch and Access the web UI
Once you have placed the weights in correct location, you can launch the UI from the terminal using the below steps.
cd /home/stable-diffusion-webui/
python launch.py --xformers
It will take few seconds to minutes, once it completes its tasks, you will find output similar to this.
Once the UI has been launched, you can access it from your dashboard.