The paradox of diffusion distillation
- Diffusion models split up the difficult task of generating data from a high-dimensional distribution into many denoising tasks, each of which is much easier.
- We train them to solve just one of these tasks at a time.
- To sample, we make many predictions in sequence.
Unverified
- Diffusion models split up the difficult task of generating data from a high-dimensional distribution into many denoising tasks, each of which is much easier.
- We train them to solve just one of these tasks at a time.
- To sample, we make many predictions in sequence.
Sources: Sander