eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers. (arXiv:2211.01324v4 [cs.CV] UPDATED)

Large-scale diffusion-based generative models have led to breakthroughs in
text-conditioned high-resolution image synthesis. Starting from random noise,
such text-to-image diffusion models gradually synthesize images in an iterative
fashion while conditioning on text prompts. We find that their synthesis
behavior qualitatively changes throughout this process: Early in sampling,
generation strongly relies on the text prompt to generate text-aligned content,
while later, the text conditioning is almost entirely ignored. This suggests
that sharing model parameters throughout the entire generation process may not …

arxiv diffusion diffusion models ediff-i ensemble expert expert denoisers image text text-to-image