Search papers, labs, and topics across Lattice.
3
0
6
Natural-language instructions can now handle both zero-shot speech synthesis and surgical acoustic editing within a single unified model, operating at 4-step distilled inference speeds without classifier-free guidance.
Goku redefines the landscape of video editing datasets by enabling complex, multi-task editing capabilities that surpass traditional single-task limitations.
Identity-preserving video generation just got a whole lot more faithful: FaithfulFaces maintains identity even under extreme pose variations and occlusions, a feat previous methods struggled with.
