consistency_models

consistency_models copied to clipboard

Hello! Your work is truly remarkable. I've had the opportunity to experiment with standard DDPM models using DDIM sampling, and despite being relatively slow, they exhibit a fascinating reversibility property. This allows for seamless transitions between Gaussian noise and images, as well as the reverse process, recreating the exact same input noise.

I would be grateful if you could provide some insights into whether this reversibility property is preserved in Consistency models. The examples provided do not explicitly demonstrate this aspect, and I am eager to learn more about it. Thank you for your time and expertise.

I think so. You can take tiny timesteps to make this exactly same formulation as diffusion models, so DDIM inversion would still work here. if it is really consistent, it should be able to reconstruct from DDIM inversion.