The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Remove unused code and torchdiffeq dependency.
comfyanonymousc910b4a01ca5
diff --git a/comfy/k_diffusion/sampling.py b/comfy/k_diffusion/sampling.pyindex 3b4e99315..dd234435f 100644--- a/comfy/k_diffusion/sampling.py+++ b/comfy/k_diffusion/sampling.py@@ -3,7 +3,6 @@ import mathfrom scipy import integrateimport torchfrom torch import nn-from torchdiffeq import odeintimport torchsdefrom tqdm.auto import trange, tqdm@@ -287,30 +286,6 @@ def sample_lms(model, x, sigmas, extra_args=None, callback=None, disable=None, oreturn x[email protected]_grad()-def log_likelihood(model, x, sigma_min, sigma_max, extra_args=None, atol=1e-4, rtol=1e-4):- extra_args = {} if extra_args is None else extra_args- s_in = x.new_ones([x.shape[0]])- v = torch.randint_like(x, 2) * 2 - 1- fevals = 0- def ode_fn(sigma, x):- nonlocal fevals- with torch.enable_grad():- x = x[0].detach().requires_grad_()- denoised = model(x, sigma * s_in, **extra_args)- d = to_d(x, sigma, denoised)- fevals += 1- grad = torch.autograd.grad((d * v).sum(), x)[0]- d_ll = (v * grad).flatten(1).sum(1)- return d.detach(), d_ll- x_min = x, x.new_zeros([x.shape[0]])- t = x.new_tensor([sigma_min, sigma_max])- sol = odeint(ode_fn, x_min, t, atol=atol, rtol=rtol, method='dopri5')- latent, delta_ll = sol[0][-1], sol[1][-1]- ll_prior = torch.distributions.Normal(0, sigma_max).log_prob(latent).flatten(1).sum(1)- return ll_prior + delta_ll, {'fevals': fevals}--class PIDStepSizeController:"""A PID controller for ODE adaptive step size control."""def __init__(self, h, pcoeff, icoeff, dcoeff, order=1, accept_safety=0.81, eps=1e-8):diff --git a/requirements.txt b/requirements.txtindex d632edf79..8ee7b83d1 100644--- a/requirements.txt+++ b/requirements.txt@@ -1,5 +1,4 @@torch-torchdiffeqtorchsdeeinopstransformers>=4.25.1