Search papers, labs, and topics across Lattice.
3
0
3
2
HPSD enables TI2V models to internalize high-quality visual cues, resulting in a remarkable boost in text-to-video performance while simultaneously enhancing image-to-video generation.
Finally, a video diffusion model that lets you insert and puppeteer consistent 3D subjects across scenes and camera angles.
Text-to-image flow models can achieve superior preference alignment by augmenting the condition space, creating a "dense" reward mapping that better captures inter-sample relationships.
