baaivision / Emu3

Next-Token Prediction is All You Need
Apache License 2.0
1.81k stars 71 forks source link

Video Model Weights Release #22

Open zpx01 opened 1 month ago

zpx01 commented 1 month ago

Hi,

When will the video model weights be available? Given that one of the main claims of Emu3 is that next-token-prediction is all we need on multimodal data (text/image/video) to achieve powerful generative models, it would be very helpful to the community if the weights could be release as soon as possible. Thank you again for your work!