It took 13 mins and counting to even start generating a 5 second snippet from the main video.
The system is RTX 5090 32GB, AMD 7950X3D, 192GB RAM.
Video is 7GB pre-enhanced (with Proteus) video however the render shows “loading model” with only 2-3% CPU - and GPU utilisation.
We expect algorithms to use high percentage if it’s making us wait in limbo for 13 mins. Or at least should stick to truth about state (for example if it already started enhancing it shouldn’t display as “loading model”)
Did it ever produce any output? There are a variety of problems in various combinations of models. Release 1.3 runs all supplied models, but does not include Starlight Precise 2,5.
Release 1.4 through 1.61 may exhibit problems with running any of the Starlight Variant (Mini, Sharp, Precise 2,5, Fast 2 and High Quality). YMMV as to which work for you. This has been an issue since 1,4 was released 2,5 months ago and is due to a new execution architecture.
In my case, in release 1.6, I can run Starlight Mini, Precise 2,5 and HQ, but Sharp and Fast 2 both fail to completely launch.
Can you grab the logs from the app and send it to the support team so we can take a look at what is going on here? help@topazlabs.com
To gather logs, please select Help > Logging > Get Logs for Support and attach the zip file to your reply.
Here is a video to help with the steps of how to collect the logs.
As Dianac mentioned, there are some known issues in various versions that the devs are working on addressing, and getting the logs will help us understand more of your situation.
