Really excited to read this paper - composing multiple diffusion models/EBMs is something I've been really interested in lately. I think there's potential in this direction for improving the controllability/interpretability of your generation process + mixing and matching pre-trained modules.
Reposted from
Kirill Neklyudov
🧵(1/7) Have you ever wanted to combine different pre-trained diffusion models but don't have time or data to retrain a new, bigger model?
🚀 Introducing SuperDiff 🦹♀️ – a principled method for efficiently combining multiple pre-trained diffusion models solely during inference!
🚀 Introducing SuperDiff 🦹♀️ – a principled method for efficiently combining multiple pre-trained diffusion models solely during inference!
Comments