The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Add DPM-Solver++(2M) SDE and exponential scheduler.
comfyanonymous069657fbf3d8
diff --git a/comfy/k_diffusion/sampling.py b/comfy/k_diffusion/sampling.pyindex c809d39fb..94d7a5762 100644--- a/comfy/k_diffusion/sampling.py+++ b/comfy/k_diffusion/sampling.py@@ -605,3 +605,46 @@ def sample_dpmpp_2m(model, x, sigmas, extra_args=None, callback=None, disable=Nox = (sigma_fn(t_next) / sigma_fn(t)) * x - (-h).expm1() * denoised_dold_denoised = denoisedreturn x+[email protected]_grad()+def sample_dpmpp_2m_sde(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, solver_type='midpoint'):+ """DPM-Solver++(2M) SDE."""++ if solver_type not in {'heun', 'midpoint'}:+ raise ValueError('solver_type must be \'heun\' or \'midpoint\'')++ sigma_min, sigma_max = sigmas[sigmas > 0].min(), sigmas.max()+ noise_sampler = BrownianTreeNoiseSampler(x, sigma_min, sigma_max) if noise_sampler is None else noise_sampler+ extra_args = {} if extra_args is None else extra_args+ s_in = x.new_ones([x.shape[0]])++ old_denoised = None+ h_last = None++ for i in trange(len(sigmas) - 1, disable=disable):+ denoised = model(x, sigmas[i] * s_in, **extra_args)+ if callback is not None:+ callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})+ if sigmas[i + 1] == 0:+ # Denoising step+ x = denoised+ else:+ # DPM-Solver++(2M) SDE+ t, s = -sigmas[i].log(), -sigmas[i + 1].log()+ h = s - t+ eta_h = eta * h++ x = sigmas[i + 1] / sigmas[i] * (-eta_h).exp() * x + (-h - eta_h).expm1().neg() * denoised++ if old_denoised is not None:+ r = h_last / h+ if solver_type == 'heun':+ x = x + ((-h - eta_h).expm1().neg() / (-h - eta_h) + 1) * (1 / r) * (denoised - old_denoised)+ elif solver_type == 'midpoint':+ x = x + 0.5 * (-h - eta_h).expm1().neg() * (1 / r) * (denoised - old_denoised)++ x = x + noise_sampler(sigmas[i], sigmas[i + 1]) * sigmas[i + 1] * (-2 * eta_h).expm1().neg().sqrt() * s_noise++ old_denoised = denoised+ h_last = h+ return xdiff --git a/comfy/samplers.py b/comfy/samplers.pyindex fccf254ec..1fb928f8d 100644--- a/comfy/samplers.py+++ b/comfy/samplers.py@@ -495,10 +495,10 @@ def encode_adm(noise_augmentor, conds, batch_size, device):class KSampler:- SCHEDULERS = ["normal", "karras", "simple", "ddim_uniform"]+ SCHEDULERS = ["normal", "karras", "exponential", "simple", "ddim_uniform"]SAMPLERS = ["euler", "euler_ancestral", "heun", "dpm_2", "dpm_2_ancestral","lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_sde",- "dpmpp_2m", "ddim", "uni_pc", "uni_pc_bh2"]+ "dpmpp_2m", "dpmpp_2m_sde", "ddim", "uni_pc", "uni_pc_bh2"]def __init__(self, model, steps, device, sampler=None, scheduler=None, denoise=None, model_options={}):self.model = model@@ -532,6 +532,8 @@ class KSampler:if self.scheduler == "karras":sigmas = k_diffusion_sampling.get_sigmas_karras(n=steps, sigma_min=self.sigma_min, sigma_max=self.sigma_max)+ elif self.scheduler == "exponential":+ sigmas = k_diffusion_sampling.get_sigmas_exponential(n=steps, sigma_min=self.sigma_min, sigma_max=self.sigma_max)elif self.scheduler == "normal":sigmas = self.model_wrap.get_sigmas(steps)elif self.scheduler == "simple":