Frank Sommers
Results
3
comments of
Frank Sommers
Yes, congrats on the release! Already loving Qwen 2.5 VL. One question about text grounding: I noticed that image segment localization works perfectly (following the cookbook examples), but text localization...
What I ended up doing was to cut a larger page (say, a letter-document page) into smaller slices and inference those smaller image patches with the model. That yields almost...
+1 This would be great.