Search papers, labs, and topics across Lattice.
4
0
3
A training-free self-guidance method can dramatically enhance output diversity in flow models without the overhead of external reward systems.
Achieving a 4x speedup in multi-reference image generation without sacrificing visual quality by intelligently dropping reference tokens.
Transforming 3D image editing from ambiguous controls to precise geometry specifications, this method allows for unprecedented accuracy in real-world applications.
Finally, text-to-image generation can handle complex 3D scenes with realistic occlusions, thanks to a clever translucent box representation that explicitly encodes hidden object regions.
