Sounds like it gets the worst of both worlds? The difficult training of a GAN with the slow runtime of a diffusion model.
"""
"Advantages over Traditional GANs" : Thus, we observe that our model exhibits _better training stability_ and mode coverage.
"Why is Sampling from Denoising Diffusion Models so Slow?" : After training, we generate novel instances by sampling from noise and iteratively denoising it _in a few steps_ using our denoising diffusion GAN generator.
"""