I have been working on my flow for these nodes, and trying to improve the speed / efficiency of the processing, see Node-red-node-annotate-image - using canvas
It's looking like a good alternative to node-red-contrib-facial-recognition certainly on my Pi5 its taking around 0.5 seconds to provide a name from CCTV still image.
I will keep tweaking and share the flow when I'm happy with it 
Copyright OpenJS Foundation and Node-RED contributors. All rights reserved. The OpenJS Foundation has registered trademarks and uses trademarks. For a list of trademarks of the OpenJS Foundation, please see our Trademark Policy and Trademark List. Trademarks and logos not indicated on the list of OpenJS Foundation trademarks are trademarksā¢ or registeredĀ® trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.
The OpenJS Foundation | Terms of Use | Privacy Policy | OpenJS Foundation Bylaws | Trademark Policy | Trademark List | Cookie Policy