PEEKABOO: Interactive Video Generation via Masked-Diffusion paper page: huggingface.co/papers/2312.07… Recently there has been a lot of progress in text-to-video generation, with state-of-the-art models being capable of generating high quality, realistic videos. However, these models

Peekaboo is a CVPR paper! 🎉 Interactively control your generated videos without re-training your t2v models! github.com/microsoft/Peek… Detailed thread soon!

We figured out a way to solve long-horizon planning problem by composing a bunch of modular diffusion models in a factor graph! This allows us to reuse the diffusion models in unseen new tasks and achieve zero-shot generalization to multi-robot collaborative manipulation tasks.