Search papers, labs, and topics across Lattice.
3
0
4
Training-free image editing can now beat fine-tuned models, thanks to a clever way of injecting visual context and ensuring concept alignment.
Achieve 7.7% better compression than JPEG-XL by using a bit-depth adaptive entropy model for lossless raw image compression.
Interpolating latent representations before decoding yields a reconstruction FID (iFID) that finally aligns with the generation FID of latent diffusion models, achieving ~0.85 correlation where standard rFID fails.
