chibop1@alien.topB to LocalLLaMAEnglish · 3 years agoVideo-LLaVA can describe both image and video input.github.comexternal-linkmessage-square6linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkVideo-LLaVA can describe both image and video input.github.comchibop1@alien.topB to LocalLLaMAEnglish · 3 years agomessage-square6linkfedilink
minus-squaresecunder73@alien.topBlinkfedilinkEnglisharrow-up1·3 years agoIf only we could use custom LLM models to write descriptions
If only we could use custom LLM models to write descriptions