Open ad-astra-video opened 2 months ago
Last commit reformats the json to return a warm and cold count for each capability/model returned by the orchestrators on discovery requests.
example of json:
{"Image to image":{"ByteDance/SDXL-Lightning":{"Cold":5,"Warm":0},"SG161222/RealVisXL_V4.0":{"Cold":1,"Warm":0},"SG161222/RealVisXL_V4.0_Lightning":{"Cold":2,"Warm":0}},"Image to video":{"stabilityai/stable-video-diffusion-img2vid-xt-1-1":{"Cold":4,"Warm":3}},"Text to image":{"ByteDance/SDXL-Lightning":{"Cold":3,"Warm":4},"ByteDance/SDXL-Lightning-4step":{"Cold":0,"Warm":1},"ByteDance/SDXL-Lightning-8step":{"Cold":0,"Warm":1},"Lykon/dreamshaper-xl-lightning":{"Cold":0,"Warm":1},"SG161222/RealVisXL_V4.0":{"Cold":1,"Warm":1},"SG161222/RealVisXL_V4.0_Lightning":{"Cold":1,"Warm":4}}}
What does this pull request do? Explain your changes. (required) Adds cli webserver endpoint to provide AI models on network in JSON.
This is a very early look at the endpoint to get feedback.
Specific updates (required)
How did you test each of these updates (required)
Does this pull request close any open issues?
Checklist:
make
runs successfully./test.sh
pass