Open pixeli99 opened 6 months ago
Hi, it seems that a simple log-normal distribution should be used to sample sigma. https://github.com/CiaraStrawberry/svd-temporal-controlnet/blob/bdd2e8fd833e2bbd83f235b6009154e4126924ad/train_svd.py#L179
Replace it with:
def rand_log_normal(shape, loc=0., scale=1., device='cpu', dtype=torch.float32): """Draws samples from an lognormal distribution.""" u = torch.rand(shape, dtype=dtype, device=device) * (1 - 2e-7) + 1e-7 return torch.distributions.Normal(loc, scale).icdf(u).exp()
Relevant discussions can be found here. https://github.com/pixeli99/SVD_Xtend/issues/21
@pixeli99 Can you provide some references for rand_log_normal function? Any paper?
Hi, it seems that a simple log-normal distribution should be used to sample sigma. https://github.com/CiaraStrawberry/svd-temporal-controlnet/blob/bdd2e8fd833e2bbd83f235b6009154e4126924ad/train_svd.py#L179
Replace it with:
Relevant discussions can be found here. https://github.com/pixeli99/SVD_Xtend/issues/21