search

remyxai / VQASynth

Compose multimodal datasets 🎹
https://twitter.com/smellslikeml/status/1756723056675094726
216 stars 13 forks source link

Point Prompting SAM2 with Molmo #27

Open smellslikeml opened 2 weeks ago

smellslikeml commented 2 weeks ago

Similar to this colab: https://colab.research.google.com/drive/1O63z-Jqi6JaXQT8gbd7ryjHwAZwZfLIb?usp=sharing

smellslikeml commented 2 weeks ago

Relates to issue: https://github.com/remyxai/VQASynth/issues/5 image

pliers image

needlenose pliers image

screwdriver image

smellslikeml commented 1 week ago

image