Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

arXiv:2403.12015v1 Announce Type: new
Abstract: Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from many-shot to single-step inference, albeit at the cost of expensive and difficult optimization due to its reliance on a fixed pretrained DINOv2 discriminator. We introduce Latent Adversarial Diffusion Distillation (LADD), a novel distillation approach overcoming the limitations of ADD. In …

abstract adversarial aim arxiv cost cs.cv diffusion diffusion models distillation driver image inference progress shift speed synthesis type video