Tag
diffusion models
6 articles
KLIP spots localized shift in inverse problems
KLIP uses KL divergence between diffusion priors and posteriors to detect and localize OOD shifts in inverse problems.
MLLMs for cleaner subject-driven image generation
This paper uses MLLMs plus VAE identity conditioning to improve subject-driven image generation and reduce copy-paste artifacts.
CARV cuts diffusion-teacher gradient variance
CARV reduces Monte Carlo variance in diffusion-teacher pipelines by reusing expensive upstream work and smarter noise sampling.
Normalizing Trajectory Models for 4-Step Generation
NTM turns few-step generation into an exact-likelihood flow model and hits strong text-to-image results in four steps.
ActCam adds joint camera and motion control
ActCam is a zero-shot way to steer both actor motion and camera path in video generation without training a new model.
Making AI Art Less Boring: Repulsion Tricks for Diverse Diffusion Images
Researchers introduce an on-the-fly repulsion mechanism in diffusion transformers that prevents mode collapse, generating more creative and diverse text-to-image results.