Besides upload and annotate [1], you can technically create your own models and use that within the Frigate configs already for free (https://docs.frigate.video/configuration/objects/#custom-mod...).

[1]You could always mount a cloud drive within Frigate's Docker config to have frigate upload camera footage to a cloud server.

A number of users have posted their experiences so far on the GitHub discussion

- https://github.com/blakeblackshear/frigate/discussions/7932#... - https://github.com/blakeblackshear/frigate/discussions/7932#... - https://github.com/blakeblackshear/frigate/discussions/7932#... - https://github.com/blakeblackshear/frigate/discussions/7932#...

I have found my frigate+ model to be much more accurate and crazy good even at night. Will be curious how things change when it snows here more often, since I've not submitted any examples of winter at this house yet.

Great write up on the version 13 experience so far with custom models: https://rogerstechtalk.com/my-frigate-v13-beta-experience/

Also an interview with the Frigate author Blake covering the custom models and the project overall: https://youtu.be/04GZBbn_nRE

I can tell you from my experience. Since I started using frigate+, I’ve had very minimal false positives. I go days without one! Even my lpr camera picks up vehicles at night. It only sees tail/head lights and the license plate, everything else is pitch black. I still get bounding boxes. Would definitely recommend it, plus it’s only going to get better

silly question but doesn't yolov8 (seganything) handle that kind of detection extremely well these days?