Comment on: Show HN: Overfitted a 900KB Transformer to Compress a 100MB CSV into 7MB

I've had this idea of building a codec that would similarly overfit to specific images. But the codec itself would not be a fixed size transformer... instead you could just mess around with the sizing to get better quality/smaller size.So the codec would be something like: <header describing image size + transformer layer shape> <transformer data itself>I've seen experiments where people have a "fixed" pipeline but I think having something more dynamic would work quite well.