Stable Diffusion 3 Medium is a state-of-the-art text-to-image model developed by Stability AI.
136
This image is designed for optimal performance on Latitude.sh servers. With just one click, you can have Stable Diffusion Forge running on a top-tier GPU.
Stable Diffusion 3 Medium is a state-of-the-art text-to-image model developed by Stability AI. It features a Multimodal Diffusion Transformer (MMDiT) architecture, significantly enhancing its ability to generate high-quality images from textual descriptions.
This Blueprint sets up a fully pre-configured environment for Stable Diffusion 3, complete with SSH support and JupyterLab for deeper manipulation. After deployment, you will receive URLs to access the WebUI and JupyterLab, along with a public IP for SSH connections.
To enable SSH access, you must input your public SSH key in the PUBLIC_KEY environment variable during deployment. After deployment, an IP address will be provided for access. Use the following command to connect:
ssh root@<APP_IP> -p 22
For optimal performance, it is highly recommended to run this on a server with GPU acceleration, such as an H100 or L40s.
| Connect Port | Internal Port | Description |
|---|---|---|
| 22 | 22 | SSH Server |
| 7860 | 7860 | SD 3 WebUI |
| 8888 | 8888 | JupyterLab |
| Variable | Description |
|---|---|
| PUBLIC_KEY | Public Key for SSH access |
| SSH_USER | Username for SSH access (default: root) |
This blueprint was designed and developed by our partner researcher:
Content type
Image
Digest
sha256:3521a37ff…
Size
14.8 GB
Last updated
about 2 years ago
docker pull latitudesh/sd-3-medium