Papers2

#ImageNet 256x256

Image Generation with a Sphere Encoder

Kaiyu Yue, Menglin Jia et al.Feb 16arXiv

The Sphere Encoder is a new way to make images fast by teaching an autoencoder to place all images evenly on a big imaginary sphere and then decode random spots on that sphere back into pictures.

#Sphere Encoder#Spherical Latent Space#RMS Normalization

Guiding a Diffusion Transformer with the Internal Dynamics of Itself

Beginner

Xingyu Zhou, Qifan Li et al.Dec 30arXiv

This paper shows a simple way to make image-generating AIs (diffusion Transformers) produce clearer, more accurate pictures by letting the model guide itself from the inside.

#Internal Guidance#Diffusion Transformer#Intermediate Supervision