For really dumb models I've also had success automatically cropping it into a grid of N images with the max size, then processing each cell individually, then once all been processed, do one final call with resized image + all other context previously generated per cell. Basically a workaround to the image dimension restrictions without loosing fidelity. Works well with even dumb 7B models.

Can't remember if I stole this idea from some existing public harness though, can't remember. If someone knows of public harnesses that do this already, please share them :)

▲

Aeroi an hour ago | parent | next [-]

i think the claude cookbook has a file that does this, called tiling.

▲

dotancohen 7 hours ago | parent | prev [-]

Does this not loose context? Especially e.g. in fonts where the character pairs 0O 1I 1l Il may be difficult to differentiate?

	▲	skeledrew 7 hours ago \| parent [-]
		That's what the grid crop should handle. The detail is retained at that level, and then everything is logically stitched together again using the lower-res-full-image as reference. That's going to be 2x token usage at minimum though.