5.3/ Dynamic Prompting: Interactively generate a story containing a sequence of events by modifying text prompts during generation. Here's a real-time demo of our UI.

5.2/ Streaming Video-to-Video Translation: Here's an example of transforming a Minecraft video into a realistic one (in real time!). In the future of gaming, maybe we could render only basic geometries, with AI video models adding all textures and lighting.

5/ Applications:
Thanks to causal dependencies, CausVid enables a wide range of additional applications without the need for fine-tuning!
5.1/ Image-to-Video: Treating an input image as the first generated frame, our method can naturally animate static images.

4/ CausVid can generate infinitely-long videos efficiently, by combining sliding window and KV-cache inference. Here we show that it produces long (30-second) videos with better quality than existing methods, while being orders of magnitude faster.

🚀 Introducing CausVid: An autoregressive video generation model that starts playing instantly as you hit 'Generate,' while also securing the 1st spot on VBench!

Project Page: causvid.github.io. More details in the long thread.