Information specific to the Stable Diffusion image generation
We provide a client interface requiring no installation and no technical expertise
I have provided a small python script with which you can use to call the horde.
- Git clone this repository
- Make sure you have python3 installed
- Open a git bash (or just bash in linux)
- Download the cli requirements with
python -m pip install -r cli_requirements.txt --user - Run
./cli_requests.py
You can use ./cli_requests.py -h to see the command line arguments to use
You can make a copy of cliRequestsData_template.py into cliRequestData.py and edit it, to use common variables for your generations. Command line arguments will always take precedence over cliRequestData.py so you can use them to tweak your generations slightly.
You can also use the REST API directly. Be aware that this will return a base64 encoded image, so it will flood your output. This is not recommended unless you know what you're doing!
curl -H "Content-Type: application/json" -H "apikey: 0000000000" -d '{"prompt":"A horde of stable robots", "params":{"n":1, "width": 256, "height": 256}}' https://stablehorde.net/api/v2/generate/sync
The "params" dictionary is the same as use by the Stable API Webui. Documentation will be forthcoming.
Pass an API Keyin order to track your usage.
You can optionally specify only specific servers to generate for you. Grab one or more server IDs from /servers and then send it with your payload as a list in the "servers" arg. Your generation will only be fulfilled by servers with the specified IDs
Anyone can convert their own PC into a worker which generates or interrogates images for other people in the horde and gains kudos for doing so. To do so, they need to run a software we call the Horde Bridged Worker, which bridges your Stable Diffusion installation to the Horde via REST API.
We have prepared a very simple installation procedure for running the bridge on each OS.