Hi TurboDiffusion team,
Your acceleration results are highly relevant to interactive world models.
We recently open-sourced AMAP-ML/DreamX-World, an interactive text/image-to-video world model where speed is tied not only to visual fidelity, but also to camera-following accuracy, scene memory, and stable autoregressive rollout.
In our setting, acceleration quality becomes especially important when users navigate through a generated world, revisit earlier viewpoints, or trigger promptable events over time.
If there is a suitable place for related community examples, we would be glad to contribute DreamX-World cases around fast controllable video generation and long-horizon consistency.
Thanks for the great work on efficient diffusion.
Hi TurboDiffusion team,
Your acceleration results are highly relevant to interactive world models.
We recently open-sourced AMAP-ML/DreamX-World, an interactive text/image-to-video world model where speed is tied not only to visual fidelity, but also to camera-following accuracy, scene memory, and stable autoregressive rollout.
In our setting, acceleration quality becomes especially important when users navigate through a generated world, revisit earlier viewpoints, or trigger promptable events over time.
If there is a suitable place for related community examples, we would be glad to contribute DreamX-World cases around fast controllable video generation and long-horizon consistency.
Thanks for the great work on efficient diffusion.