Search papers, labs, and topics across Lattice.
3
0
2
Composing concepts as separate image layers in LILAC eliminates identity confusion in multi-concept diffusion models, achieving superior results without joint retraining.
Aggregating gradients from multiple views can dramatically enhance 3D generation performance while cutting optimization steps in half.
Achieving a 76% boost in decorative font generation without sacrificing text legibility, FontFusion redefines typography in diffusion models.
