The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Some optimizations to euler a.
comfyanonymousc1b92b719d3e
diff --git a/comfy/k_diffusion/sampling.py b/comfy/k_diffusion/sampling.pyindex 2838b50c7..f08370f83 100644--- a/comfy/k_diffusion/sampling.py+++ b/comfy/k_diffusion/sampling.py@@ -175,12 +175,14 @@ def sample_euler_ancestral(model, x, sigmas, extra_args=None, callback=None, dissigma_down, sigma_up = get_ancestral_step(sigmas[i], sigmas[i + 1], eta=eta)if callback is not None:callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})- d = to_d(x, sigmas[i], denoised)- # Euler method- dt = sigma_down - sigmas[i]- x = x + d * dt- if sigmas[i + 1] > 0:- x = x + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * sigma_up++ if sigma_down == 0:+ x = denoised+ else:+ d = to_d(x, sigmas[i], denoised)+ # Euler method+ dt = sigma_down - sigmas[i]+ x = x + d * dt + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * sigma_upreturn x@torch.no_grad()@@ -192,19 +194,22 @@ def sample_euler_ancestral_RF(model, x, sigmas, extra_args=None, callback=None,for i in trange(len(sigmas) - 1, disable=disable):denoised = model(x, sigmas[i] * s_in, **extra_args)# sigma_down, sigma_up = get_ancestral_step(sigmas[i], sigmas[i + 1], eta=eta)- downstep_ratio = 1 + (sigmas[i+1]/sigmas[i] - 1) * eta- sigma_down = sigmas[i+1] * downstep_ratio- alpha_ip1 = 1 - sigmas[i+1]- alpha_down = 1 - sigma_down- renoise_coeff = (sigmas[i+1]**2 - sigma_down**2*alpha_ip1**2/alpha_down**2)**0.5if callback is not None:callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})- # Euler method- sigma_down_i_ratio = sigma_down / sigmas[i]- x = sigma_down_i_ratio * x + (1 - sigma_down_i_ratio) * denoised- if sigmas[i + 1] > 0 and eta > 0:- x = (alpha_ip1/alpha_down) * x + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * renoise_coeff+ if sigmas[i + 1] == 0:+ x = denoised+ else:+ downstep_ratio = 1 + (sigmas[i + 1] / sigmas[i] - 1) * eta+ sigma_down = sigmas[i + 1] * downstep_ratio+ alpha_ip1 = 1 - sigmas[i + 1]+ alpha_down = 1 - sigma_down+ renoise_coeff = (sigmas[i + 1]**2 - sigma_down**2 * alpha_ip1**2 / alpha_down**2)**0.5+ # Euler method+ sigma_down_i_ratio = sigma_down / sigmas[i]+ x = sigma_down_i_ratio * x + (1 - sigma_down_i_ratio) * denoised+ if eta > 0:+ x = (alpha_ip1 / alpha_down) * x + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * renoise_coeffreturn x@torch.no_grad()