search

baaivision / Emu

Emu Series: Generative Multimodal Models from BAAI
https://baaivision.github.io/emu2/
Apache License 2.0
1.61k stars 84 forks source link

Generate video from any prompt sequence #46

Open zhw-zhang opened 9 months ago

zhw-zhang commented 9 months ago

Hello, I saw on the project page that you showed the Generate video from any prompt sequence function, but I didn't seem to see this function in the demo. Will you launch this function?

nick-lambdalabs commented 9 months ago

Based on the paper, I believe there is both an image decoder model and a video decoder model that appear not to have been released yet. Hoping they release them soon, since this is potentially a killer feature of this model.

SlotherCui commented 9 months ago

Thank you for your interest and inquiry. Indeed, we have both an image decoder and a video decoder model. The Emu2-Gen with image decoder has already been released(https://huggingface.co/BAAI/Emu2-Gen). As for the video decoder, we plan to release it soon. We are currently working on organizing the inference code for video generation and aim to make it available as promptly as possible.

zhw-zhang commented 8 months ago

Thank you for your reply. If the model of the video is open source, can you remind me here? It's important to me.

TsuTikgiau commented 4 months ago

Hello Team, thank you for the cool project! May I ask when you plan to release the video generation decoder? Thank you!