Abstract: Diffusion models (DM) can gradually learn to remove noise, which have been widely used in artificial intelligence generated content (AIGC) in recent years. The property of DM for eliminating ...

A fork of stable-dreamfusion that adds ControlNet guidance to enable conditioning of 3d generation on user scribble. Includes zero1to3 support with ControlNet. This work is based on an increasing list ...

Abstract: Synthetically-generated images are getting increasingly popular. Diffusion models have advanced to the stage where even non-experts can generate photo-realistic images from a simple text ...

Diffusion policy exhibits promising multimodal property and distributional expressivity in robotic field, while not ready for real-time end-to-end autonomous driving in more dynamic and open-world ...