FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention

A woman carrying a bouquet of vibrant flowers walks along the beach A man and a woman are standing together in a forested area

A young woman wearing a white t-shirt is sitting indoors.

Figure 1. FullDiT is a multi-task video generative foundation model that unifies conditional learning with full self-attention. With self-attention's long-context learning ability, FullDiT can flexibly take different combinations of input to generate high-quality videos.