298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-01-25 15:55:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add DPM-Solver++(2M) SDE and exponential scheduler.

Browse Source 
exponential scheduler is the one recommended with this sampler.
This commit is contained in:
comfyanonymous 2023-05-21 01:35:08 -04:00
parent 516119ad83
commit 069657fbf3
2 changed files with 47 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
comfy/k_diffusion/sampling.py
View File

@ -605,3 +605,46 @@ def sample_dpmpp_2m(model, x, sigmas, extra_args=None, callback=None, disable=No
x = (sigma_fn(t_next) / sigma_fn(t)) * x - (-h).expm1() * denoised_d
old_denoised = denoised
return x
@torch.no_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 x

6
comfy/samplers.py
View File

@ -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":