Reverse sampling for schedulers

Model/Pipeline/Scheduler description

Some of the samplers (e.g. DDIM) are fully reversible. A simple API addition of reverse_step() or a mixin can be implemented. This will allow interpolating between images not generated by diffusion models.

Open source status

• The model implementation is available
• The model weights are available (Only relevant if addition is not a scheduler).

Provide useful links for the implementation

https://github.com/crowsonkb/v-diffusion-jax/blob/master/diffusion/sampling.py by @crowsonkb implements reverse sampling for V-objective diffusionon

[neverix]

For just DDIM this would work - but the code is pretty much the same between the forward and reverse process, so I think inheriting or adding it as a method for the DDIM scheduler would work better. I’ll implement the rest of the paper in the notebook and write back

[neverix]

The code for this is in the Colab linked above