I am using DeepFloyd locally with Stage I medium, T5 medium, and stage II medium. I noticed that if I were to modify the variance scheduler for sampling to linear from cosine, the sample results are much worse than with a cosine scheduler.
Is there a reason why this happens? And, is there a way DeepFloyd can work well with a linear scheduler too?
I am using DeepFloyd locally with Stage I medium, T5 medium, and stage II medium. I noticed that if I were to modify the variance scheduler for sampling to linear from cosine, the sample results are much worse than with a cosine scheduler.
Is there a reason why this happens? And, is there a way DeepFloyd can work well with a linear scheduler too?