Finetune SVD with discrete time noise scheduler

[HL-hanlin]

Hi, thanks for your great training code for SVD!

When I switch the default SVD sampler into discrete noise scheduler, the generated video looks very bad.
May I ask which layers/parameters of SVD should I finetune to make it compatible with discrete time noise scheduler? Or are there some ways that can transform the SVD noisy_latents (which is equal to latents + sigma * noise, with large sigma values) into corresponding noisy_latents (with smaller sigmas) used to train on discrete noise schedulers?

Thanks!

[pixeli99]

You should need the FT timestep condition, you can refer to this part of the SVD paper for some help

[HL-hanlin]

Got it! Thanks for the pointer!