mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-07-27 08:16:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Separate denoised and noise estimation in Euler CFG++ (#9008)

Browse Source 
This will change their behavior with the sampling CONST type.
It also combines euler_cfg_pp and euler_ancestral_cfg_pp into one main function.
This commit is contained in:
chaObserv 2025-07-24 07:47:05 +08:00 committed by GitHub
parent e78d230496
commit e729a5cc11
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 32 additions and 32 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
comfy/k_diffusion/sampling.py
View File

@ -1210,39 +1210,21 @@ def sample_deis(model, x, sigmas, extra_args=None, callback=None, disable=None,
return x_next return x_next
@torch.no_grad()
def sample_euler_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None):
extra_args = {} if extra_args is None else extra_args
temp = [0]
def post_cfg_function(args):
temp[0] = args["uncond_denoised"]
return args["denoised"]
model_options = extra_args.get("model_options", {}).copy()
extra_args["model_options"] = comfy.model_patcher.set_model_options_post_cfg_function(model_options, post_cfg_function, disable_cfg1_optimization=True)
s_in = x.new_ones([x.shape[0]])
for i in trange(len(sigmas) - 1, disable=disable):
sigma_hat = sigmas[i]
denoised = model(x, sigma_hat * s_in, **extra_args)
d = to_d(x, sigma_hat, temp[0])
if callback is not None:
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigma_hat, 'denoised': denoised})
# Euler method
x = denoised + d * sigmas[i + 1]
return x
@torch.no_grad() @torch.no_grad()
def sample_euler_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None): def sample_euler_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None):
"""Ancestral sampling with Euler method steps.""" """Ancestral sampling with Euler method steps (CFG++)."""
extra_args = {} if extra_args is None else extra_args extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None) seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
temp = [0] model_sampling = model.inner_model.model_patcher.get_model_object("model_sampling")
lambda_fn = partial(sigma_to_half_log_snr, model_sampling=model_sampling)
uncond_denoised = None
def post_cfg_function(args): def post_cfg_function(args):
temp[0] = args["uncond_denoised"] nonlocal uncond_denoised
uncond_denoised = args["uncond_denoised"]
return args["denoised"] return args["denoised"]
model_options = extra_args.get("model_options", {}).copy() model_options = extra_args.get("model_options", {}).copy()
@ -1251,15 +1233,33 @@ def sample_euler_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback=No
s_in = x.new_ones([x.shape[0]]) s_in = x.new_ones([x.shape[0]])
for i in trange(len(sigmas) - 1, disable=disable): for i in trange(len(sigmas) - 1, disable=disable):
denoised = model(x, sigmas[i] * s_in, **extra_args) denoised = model(x, sigmas[i] * s_in, **extra_args)
sigma_down, sigma_up = get_ancestral_step(sigmas[i], sigmas[i + 1], eta=eta)
if callback is not None: if callback is not None:
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised}) callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})
d = to_d(x, sigmas[i], temp[0]) if sigmas[i + 1] == 0:
# Denoising step
x = denoised
else:
alpha_s = sigmas[i] * lambda_fn(sigmas[i]).exp()
alpha_t = sigmas[i + 1] * lambda_fn(sigmas[i + 1]).exp()
d = to_d(x, sigmas[i], alpha_s * uncond_denoised) # to noise
# DDIM stochastic sampling
sigma_down, sigma_up = get_ancestral_step(sigmas[i] / alpha_s, sigmas[i + 1] / alpha_t, eta=eta)
sigma_down = alpha_t * sigma_down
# Euler method # Euler method
x = denoised + d * sigma_down x = alpha_t * denoised + sigma_down * d
if sigmas[i + 1] > 0: if eta > 0 and s_noise > 0:
x = x + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * sigma_up x = x + alpha_t * noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * sigma_up
return x return x
@torch.no_grad()
def sample_euler_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None):
"""Euler method steps (CFG++)."""
return sample_euler_ancestral_cfg_pp(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=0.0, s_noise=0.0, noise_sampler=None)
@torch.no_grad() @torch.no_grad()
def sample_dpmpp_2s_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None): def sample_dpmpp_2s_ancestral_cfg_pp(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None):
"""Ancestral sampling with DPM-Solver++(2S) second-order steps.""" """Ancestral sampling with DPM-Solver++(2S) second-order steps."""