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 interchangeable 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.

API

• 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 specific.

Examples

• 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.