Hi Team, Great work! I have a silly question, after reading the paper. it seems you only finetune the part of the Chameleon last head . But in order to generate image, one also needs to have VQGAN's decoder. How do you have this decoder? Did you train this model or Chameleon released this model? Thanks
Hi Team, Great work! I have a silly question, after reading the paper. it seems you only finetune the part of the Chameleon last head . But in order to generate image, one also needs to have VQGAN's decoder. How do you have this decoder? Did you train this model or Chameleon released this model? Thanks