It’s my first experience with the CLI. Artemis model over CLI worked but I can’t start Starlight mini over the CLI and get idx (start end frame) argument error. I did copy/paste this from the TVAI GUI output prompt. Where is the fault?
They have not added CLI support for it yet.
There’s probably a way to do it, but it’s most likely not through their ffmpeg.
Starlight Mini is not currently an option for CLI with the app, it is being run via a different process right now.
This will be changed in the future once the team gets the workflow sorted out and running efficiently.
1 Like
Thanks for the answers! Then I have to wait, would be nice when we get this. I tested a little bit and thinking I was close, but i did not work. The process starts sucessfully but then I get message videofiles could not be recognized. Here is my fail try
%ProgramData%\Topaz Labs LLC\Topaz Video AI\models\runner.exe sample_source.mp4 sample_out.mp4 --start-frame-idx 0 --end-frame-idx 64 --ffmpeg-encoding "-c:v h264_nvenc -profile:v high -pix_fmt yuv420p -g 15 -preset p7 -tune hq -rc constqp -qp 18 -rc-lookahead 10 -spatial_aq 1 -aq-strength 15 -b:v 0 -movflags frag_keyframe+empty_moov+delay_moov+use_metadata_tags+write_colr -bf 0" --ffmpeg-preproc-filters scale=w=640:h=480,setsar=1 --upscale-factor 3 --**max-gpu-mem 16**So the last parameter is interesting, you set freely set max gpu RAM and override gpu ram detection, for people who has low usage or want’s more gets shared for quality 
