Cary Knoop

When a source is too low quality, for instance when it has a lot of compression noise, this noise will only get amplified.

Here is are two examples of Tecogan processed (among a lot of other things) SD interlaced videos: https://youtu.be/1ZwPe7YgiCY https://youtu.be/SKyrZiKVRvU

It looks like it is chroma subsampling related. I would make sure your generated images from the video are sampled from 4:2:0 through 4:4:4 to RGB correctly.

> Change PORT and MODEL to whatever you want `interpreter -ab http://localhost:PORT/v1 --model openai/MODEL` Further documentation is here: https://docs.openinterpreter.com/usage/terminal/arguments I would think an example using a port in addition to...

Tecogan runs fine on Windows 10. For a 2080Ti the maximum is slightly over SD video size.

A kludgy solution is to write a magic string (i.e. something that does not naturally exist in a text - for instance 'xx2yyjjkkll4324') after a paragraph and filter it after...