Pengxiang Li
Pengxiang Li
You should need the FT timestep condition, you can refer to this part of the SVD paper for some help 
The LoRA training is not yet supported, so this parameter is temporarily ineffective, but I will support it in the future.
Hi, I didn't quite understand what you meant. Are you asking why the `encoder_hidden_states` need to be replaced with `zeros`?
Hi, actually I don't quite understand your motivation. Are you looking to change the sampling method of SVD to DDIM?
Thank you very much for raising this question, This was due to an oversight on my part, as I originally thought that sigma in the code followed a simple log-normal...
Regarding the second question, it is solely because I have been lazy that I will complete this section of the code.
> @pixeli99 Thanks for your work. I have a similar question, why you chose the `rand_cosine_interpolated` noise scheduler instead of the one mentioned in the `EDM (Karras et al.)` paper....
I understand what you're saying, but I think that different sigma distributions correspond to different diffusion paths. In theory, would it be possible to use the same sampler for sampling?...
@m-muaz I haven't tried it yet, but if I make any progress, I will update here.
I roughly understand what you mean, I might still need to read carefully to grasp the principle here, thank you very much for your reply.