Hierarchically branched diffusion models leverage dataset structure for class-conditional generation

1 code implementation • 21 Dec 2022 • Alex M. Tseng, Max Shen, Tommaso Biancalani, Gabriele Scalia

We highlight several advantages of branched diffusion models over the current state-of-the-art methods for class-conditional diffusion, including extension to novel classes in a continual-learning setting, a more sophisticated form of analogy-based conditional generation (i. e. transmutation), and a novel interpretability into the generation process.

Continual Learning