Use torch.special.expm1 (#6388)

* Use `torch.special.expm1`

This function provides greater precision than `exp(x) - 1` for small values of `x`.

Found with TorchFix https://github.com/pytorch-labs/torchfix/

* Use non-alias

comfy/k_diffusion/sampling.py

@@ -40,7 +40,7 @@ def get_sigmas_polyexponential(n, sigma_min, sigma_max, rho=1., device='cpu'):
 def get_sigmas_vp(n, beta_d=19.9, beta_min=0.1, eps_s=1e-3, device='cpu'):
     """Constructs a continuous VP noise schedule."""
     t = torch.linspace(1, eps_s, n, device=device)
-    sigmas = torch.sqrt(torch.exp(beta_d * t ** 2 / 2 + beta_min * t) - 1)
+    sigmas = torch.sqrt(torch.special.expm1(beta_d * t ** 2 / 2 + beta_min * t))
     return append_zero(sigmas)