schedulers

Schedulers

Schedulers are the algorithms to use diffusion models in inference as well as for training. They include the noise schedules and define algorithm-specific diffusion steps.
Schedulers can be used interchangable between diffusion models in inference to find the preferred trade-off between speed and generation quality.
Schedulers are available in numpy, but can easily be transformed into PyTorch.

Schedulers should provide one or more def step(...) functions that should be called iteratively to unroll the diffusion loop during the forward pass.
Schedulers should be framework-agnostic, but provide a simple functionality to convert the scheduler into a specific framework, such as PyTorch with a set_format(...) method.

The DDPM scheduler was proposed in Denoising Diffusion Probabilistic Models and can be found in scheduling_ddpm.py. An example of how to use this scheduler can be found in pipeline_ddpm.py.
The DDIM scheduler was proposed in Denoising Diffusion Implicit Models and can be found in scheduling_ddim.py. An example of how to use this scheduler can be found in pipeline_ddim.py.
The PNDM scheduler was proposed in Pseudo Numerical Methods for Diffusion Models on Manifolds and can be found in scheduling_pndm.py. An example of how to use this scheduler can be found in pipeline_pndm.py.