298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-04-12 18:33:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge 6fc0c7fc35 into 22ad513c72

Browse Source
This commit is contained in:
chaObserv 2025-04-12 08:49:51 +00:00 committed by GitHub
commit d0cddc8b27
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 99 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

98
comfy/k_diffusion/sampling.py
View File

@ -1422,3 +1422,101 @@ def sample_er_sde(model, x, sigmas, extra_args=None, callback=None, disable=None
x = x + noise_sampler(sigmas[i], sigmas[i + 1]) * s_noise * (sigmas[i + 1] ** 2 - sigmas[i] ** 2 * r ** 2).sqrt().nan_to_num(nan=0.0)
old_denoised = denoised
return x
@torch.no_grad()
def sample_seeds_2(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, r=0.5):
'''
SEEDS-2 - Stochastic Explicit Exponential Derivative-free Solvers (VE Data Prediction) stage 2
Arxiv: https://arxiv.org/abs/2305.14267
'''
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_in = x.new_ones([x.shape[0]])
inject_noise = eta > 0 and s_noise > 0
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:
x = denoised
else:
t, t_next = -sigmas[i].log(), -sigmas[i + 1].log()
h = t_next - t
h_eta = h * (eta + 1)
s = t + r * h
fac = 1 / (2 * r)
sigma_s = s.neg().exp()
coeff_1, coeff_2 = (-r * h_eta).expm1(), (-h_eta).expm1()
if inject_noise:
noise_coeff_1 = (-2 * r * h * eta).expm1().neg().sqrt()
noise_coeff_2 = ((-2 * r * h * eta).expm1() - (-2 * h * eta).expm1()).sqrt()
noise_1, noise_2 = noise_sampler(sigmas[i], sigma_s), noise_sampler(sigma_s, sigmas[i + 1])
# Step 1
x_2 = (coeff_1 + 1) * x - coeff_1 * denoised
if inject_noise:
x_2 = x_2 + sigma_s * (noise_coeff_1 * noise_1) * s_noise
denoised_2 = model(x_2, sigma_s * s_in, **extra_args)
# Step 2
denoised_d = (1 - fac) * denoised + fac * denoised_2
x = (coeff_2 + 1) * x - coeff_2 * denoised_d
if inject_noise:
x = x + sigmas[i + 1] * (noise_coeff_2 * noise_1 + noise_coeff_1 * noise_2) * s_noise
return x
@torch.no_grad()
def sample_seeds_3(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, r_1=1./3, r_2=2./3):
'''
SEEDS-3 - Stochastic Explicit Exponential Derivative-free Solvers (VE Data Prediction) stage 3
Arxiv: https://arxiv.org/abs/2305.14267
'''
extra_args = {} if extra_args is None else extra_args
seed = extra_args.get("seed", None)
noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
s_in = x.new_ones([x.shape[0]])
inject_noise = eta > 0 and s_noise > 0
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:
x = denoised
else:
t, t_next = -sigmas[i].log(), -sigmas[i + 1].log()
h = t_next - t
h_eta = h * (eta + 1)
s_1 = t + r_1 * h
s_2 = t + r_2 * h
sigma_s_1, sigma_s_2 = s_1.neg().exp(), s_2.neg().exp()
coeff_1, coeff_2, coeff_3 = (-r_1 * h_eta).expm1(), (-r_2 * h_eta).expm1(), (-h_eta).expm1()
if inject_noise:
noise_coeff_1 = (-2 * r_1 * h * eta).expm1().neg().sqrt()
noise_coeff_2 = ((-2 * r_1 * h * eta).expm1() - (-2 * r_2 * h * eta).expm1()).sqrt()
noise_coeff_3 = ((-2 * r_2 * h * eta).expm1() - (-2 * h * eta).expm1()).sqrt()
noise_1, noise_2, noise_3 = noise_sampler(sigmas[i], sigma_s_1), noise_sampler(sigma_s_1, sigma_s_2), noise_sampler(sigma_s_2, sigmas[i + 1])
# Step 1
x_2 = (coeff_1 + 1) * x - coeff_1 * denoised
if inject_noise:
x_2 = x_2 + sigma_s_1 * (noise_coeff_1 * noise_1) * s_noise
denoised_2 = model(x_2, sigma_s_1 * s_in, **extra_args)
# Step 2
x_3 = (coeff_2 + 1) * x - coeff_2 * denoised + (r_2 / r_1) * (coeff_2 / (r_2 * h_eta) + 1) * (denoised_2 - denoised)
if inject_noise:
x_3 = x_3 + sigma_s_2 * (noise_coeff_2 * noise_1 + noise_coeff_1 * noise_2) * s_noise
denoised_3 = model(x_3, sigma_s_2 * s_in, **extra_args)
# Step 3
x = (coeff_3 + 1) * x - coeff_3 * denoised + (1. / r_2) * (coeff_3 / h_eta + 1) * (denoised_3 - denoised)
if inject_noise:
x = x + sigmas[i + 1] * (noise_coeff_3 * noise_1 + noise_coeff_2 * noise_2 + noise_coeff_1 * noise_3) * s_noise
return x

2
comfy/samplers.py
View File

@ -710,7 +710,7 @@ KSAMPLER_NAMES = ["euler", "euler_cfg_pp", "euler_ancestral", "euler_ancestral_c
"lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_2s_ancestral_cfg_pp", "dpmpp_sde", "dpmpp_sde_gpu",
"dpmpp_2m", "dpmpp_2m_cfg_pp", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm", "lcm",
"ipndm", "ipndm_v", "deis", "res_multistep", "res_multistep_cfg_pp", "res_multistep_ancestral", "res_multistep_ancestral_cfg_pp",
"gradient_estimation", "er_sde"]
"gradient_estimation", "er_sde", "seeds_2", "seeds_3"]
class KSAMPLER(Sampler):
def __init__(self, sampler_function, extra_options={}, inpaint_options={}):