No, I haven not work on this since the AI integrated in Blue Iris works extremely well. Most likely I will work on the models sometime in the next couple of months.
There might be a Blue Iris issue with using CodeProject.AI since they have built-in AI, what I can see it should work for you. Have you tried using the built-in AI, it works well, that is what I am currently using.
I found some of the new drivers did not work well, that might be your issue, I am using the below driver
https://www.nvidia.com/en-us/geforce/drivers/results/257327/
What model are you using and how many models are being used for the camera? Also make sure you uncheck Use main stream, it does not improve accuracy, it just slow down the detection. Below are the times I am getting with my RTX 5090
I had an issue with the cameras connecting to a local NTP server, the fix that work for me was the network needs to be set to private and make sure your firewall is not blocking port 123.
All of the models are trained for an input image with a resolution of 640 x 640. The best sub stream setting are 704 x 480 (D1) or 640 x 480 (VGA), I am using 704 x 480 (D1) which closely matches the aspect ratio of main stream
Did you try this, selecting only one model to see if one model works
https://ipcamtalk.com/threads/installed-object-detection-yolo11-net.84708/post-975694
Try just using one model, how to select one model shown in the below post. After making the changes reboot CP.AI server, once the CP.AI is up and running reboot the BI server and see if just one model works.
https://ipcamtalk.com/threads/installed-object-detection-yolo11-net.84708/post-975694