ClipTagger 12bImage text to textModelClipTagger-12bImage text to text model.gemma3vlmvideo-understanding6063apache-2.015 mo agoIinference-netShare or keepTake it
PozifyComputer visionDemoPozifySmall-model workout form review from short videos.gradiocomputer-visionpose-estimationRuns in the browser on Hugging Face95 mo agoBbuild-small-hackathonShare or keepTry it