← Back to context Comment by energy123 2 days ago Yeah, once it gets converted into tokens how does "zooming in" somehow increase information content? 1 comment energy123 Reply nutrientharvest 2 days ago It's cropping the original image then tokenizing it again with less downsampling, not cropping its internal representation.
nutrientharvest 2 days ago It's cropping the original image then tokenizing it again with less downsampling, not cropping its internal representation.
It's cropping the original image then tokenizing it again with less downsampling, not cropping its internal representation.