Running Sogni Fast Worker Remotely

How to run Sogni Fast Worker on a Distributed GPU Cloud platform

Don't have your own local Nvidia box to run Sogni Fast Worker with? This Worker is also designed to be deployable to any cloud GPU rental service which supports loading custom Docker images.

Sogni Fast Worker supports running on Distributed GPU Cloud Platforms. Nosana.com and Salad.com integrations have been well tested. Your mileage may vary with other platforms.

Running on Salad.com

Create a Sogni account if you don't have one already. You may create one at app.sogni.ai. Multiple Sogni Fast Workers can be run from one account or seperate accounts.
Log in to nft.sogni.ai and mint a free Sogni NFT for each GPU worker you want to deploy. Record the NFT Token ID and the API Key for each worker. The API Key is unique to the Sogni Account. The NFT Token ID will be unique for each worker.
Sign up for a Salad account using the "Deploy on SaladCloud" option and follow their website instructions to create a new Container Group.
Under "Container Configuration" set the Image Source to sogni/sogni-flux-worker:latest to spawn a Flux worker. sogni/sogni-stable-diffusion-worker:latest for a Stable Diffusion worker.
Under Replica Count you will always leave this at 1. If you are running multiple workers you will need to create a new Container Group for each worker as Salad.com passes Environment Variables at the Container Group level.
For vCPUs select 4. For Memory select 30 GB. For GPU select "RTX 4090" or "RTX 5090". For Disk Space select the maximum size available for model caching.
For Health Check Probes: Startup Probe, select Protocol: "HTTP/1.X" and Path "/startup". Port 8000. Initial Delay Seconds: 90. Period Seconds: 5, Timeout Seconds: 5, Success Threshold: 2, Failure Threshold: 120.
For Liveness Prove select Protocol: "HTTP/1.X" and Path "/liveness". Port 8000. Initial Delay Seconds: 90. Period Seconds: 10, Timeout Seconds: 30, Success Threshold: 1, Failure Threshold: 6. Note: If your platform does not support health probes you can skip steps 7 and 8, Sogni Worker has it's own internal health probes to fallback on.
Under "Environment Variables" add the following:
- API_KEY: The API Key for your Sogni Account.
- NFT_TOKEN_ID: The NFT Token ID for your Sogni worker.
- AUTO_DOWNLOAD_TO_MIN_MODEL_COUNT: The number of models to download when the worker starts. Ignored for the Flux worker which has models preloaded.
- DATA_DOG_API_KEY: You may supply an optional DataDog API Key for troubleshooting.
Click "Deploy" and your worker will start. You check for latest integrations documentation at docs.sogni.ai and reach out at app@sogni.ai for any additional assistance.

Need help? Join our Discord!

If you have any issues or questions setting up your Sogni Fast Worker you can reach out on Discord or via email to app@sogni.ai for technical support. Join Sogni Discord ✨

PreviousRunning Sogni Fast Worker Locally NextSogni Fast Worker Advanced Configuration

Last updated 4 days ago

Was this helpful?

Running on Salad.com

Create a Sogni account if you don't have one already. You may create one at app.sogni.ai. Multiple Sogni Fast Workers can be run from one account or seperate accounts.

Log in to nft.sogni.ai and mint a free Sogni NFT for each GPU worker you want to deploy. Record the NFT Token ID and the API Key for each worker. The API Key is unique to the Sogni Account. The NFT Token ID will be unique for each worker.

Sign up for a Salad account using the "Deploy on SaladCloud" option and follow their website instructions to create a new Container Group.

Under "Container Configuration" set the Image Source to sogni/sogni-flux-worker:latest to spawn a Flux worker. sogni/sogni-stable-diffusion-worker:latest for a Stable Diffusion worker.

Under Replica Count you will always leave this at 1. If you are running multiple workers you will need to create a new Container Group for each worker as Salad.com passes Environment Variables at the Container Group level.

For vCPUs select 4. For Memory select 30 GB. For GPU select "RTX 4090" or "RTX 5090". For Disk Space select the maximum size available for model caching.

For Health Check Probes: Startup Probe, select Protocol: "HTTP/1.X" and Path "/startup". Port 8000. Initial Delay Seconds: 90. Period Seconds: 5, Timeout Seconds: 5, Success Threshold: 2, Failure Threshold: 120.

For Liveness Prove select Protocol: "HTTP/1.X" and Path "/liveness". Port 8000. Initial Delay Seconds: 90. Period Seconds: 10, Timeout Seconds: 30, Success Threshold: 1, Failure Threshold: 6. Note: If your platform does not support health probes you can skip steps 7 and 8, Sogni Worker has it's own internal health probes to fallback on.

Under "Environment Variables" add the following:

API_KEY: The API Key for your Sogni Account.
NFT_TOKEN_ID: The NFT Token ID for your Sogni worker.
AUTO_DOWNLOAD_TO_MIN_MODEL_COUNT: The number of models to download when the worker starts. Ignored for the Flux worker which has models preloaded.
DATA_DOG_API_KEY: You may supply an optional DataDog API Key for troubleshooting.

Click "Deploy" and your worker will start. You check for latest integrations documentation at docs.sogni.ai and reach out at app@sogni.ai for any additional assistance.