You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have a naive question about the objective "pred_x_start". If we use this objective, after training we have a model that can directly denoise from any timestep xt to x0. In this case, what is the purpose of reverse diffusion process with >1 timesteps?
There are essentially two possible outcomes after training:
We have a well trained and PERFECT denoising model that always gives ideal x0. The reverse diffusion seems to be a waste of time adding noise to the perfect x0 at each timestep.
We have a regular denoising model that gives approximately optimal x0. However, the reverse diffusion will keep adding noise during the process. This is like adding extra error (noise) on top of existing approximation error, which seems to make it even harder for the model to denoise.
Best,
Leo
The text was updated successfully, but these errors were encountered:
To clarify, the p(x(t-1)|xt) is the denoise step in most papers, which may be unncessary as discussed. As Eq. 9 in https://arxiv.org/pdf/2107.00630.pdf, the well trained model by "predict_x_start" is already capable of producing x0 from xt.
Hi diffusion developers,
Thank you for the open source development!
I have a naive question about the objective "pred_x_start". If we use this objective, after training we have a model that can directly denoise from any timestep xt to x0. In this case, what is the purpose of reverse diffusion process with >1 timesteps?
There are essentially two possible outcomes after training:
Best,
Leo
The text was updated successfully, but these errors were encountered: