|
import torch |
|
import tqdm |
|
import k_diffusion.sampling |
|
from modules import sd_samplers_common, sd_samplers_kdiffusion, sd_samplers |
|
from tqdm.auto import trange, tqdm |
|
from k_diffusion import utils |
|
from k_diffusion.sampling import to_d |
|
import math |
|
from importlib import import_module |
|
|
|
sampling = import_module("k_diffusion.sampling") |
|
NAME = 'Euler_Negative' |
|
ALIAS = 'euler_negative' |
|
|
|
|
|
|
|
|
|
|
|
class _Rescaler: |
|
def __init__(self, model, x, mode, **extra_args): |
|
self.model = model |
|
self.x = x |
|
self.mode = mode |
|
self.extra_args = extra_args |
|
self.init_latent, self.mask, self.nmask = model.init_latent, model.mask, model.nmask |
|
|
|
def __enter__(self): |
|
if self.init_latent is not None: |
|
self.model.init_latent = torch.nn.functional.interpolate(input=self.init_latent, size=self.x.shape[2:4], mode=self.mode) |
|
if self.mask is not None: |
|
self.model.mask = torch.nn.functional.interpolate(input=self.mask.unsqueeze(0), size=self.x.shape[2:4], mode=self.mode).squeeze(0) |
|
if self.nmask is not None: |
|
self.model.nmask = torch.nn.functional.interpolate(input=self.nmask.unsqueeze(0), size=self.x.shape[2:4], mode=self.mode).squeeze(0) |
|
|
|
return self |
|
|
|
def __exit__(self, type, value, traceback): |
|
del self.model.init_latent, self.model.mask, self.model.nmask |
|
self.model.init_latent, self.model.mask, self.model.nmask = self.init_latent, self.mask, self.nmask |
|
|
|
|
|
@torch.no_grad() |
|
def dy_sampling_step(x, model, dt, sigma_hat, **extra_args): |
|
original_shape = x.shape |
|
batch_size, channels, m, n = original_shape[0], original_shape[1], original_shape[2] // 2, original_shape[3] // 2 |
|
extra_row = x.shape[2] % 2 == 1 |
|
extra_col = x.shape[3] % 2 == 1 |
|
|
|
if extra_row: |
|
extra_row_content = x[:, :, -1:, :] |
|
x = x[:, :, :-1, :] |
|
if extra_col: |
|
extra_col_content = x[:, :, :, -1:] |
|
x = x[:, :, :, :-1] |
|
|
|
a_list = x.unfold(2, 2, 2).unfold(3, 2, 2).contiguous().view(batch_size, channels, m * n, 2, 2) |
|
c = a_list[:, :, :, 1, 1].view(batch_size, channels, m, n) |
|
|
|
with _Rescaler(model, c, 'nearest-exact', **extra_args) as rescaler: |
|
denoised = model(c, sigma_hat * c.new_ones([c.shape[0]]), **rescaler.extra_args) |
|
d = sampling.to_d(c, sigma_hat, denoised) |
|
c = c + d * dt |
|
|
|
d_list = c.view(batch_size, channels, m * n, 1, 1) |
|
a_list[:, :, :, 1, 1] = d_list[:, :, :, 0, 0] |
|
x = a_list.view(batch_size, channels, m, n, 2, 2).permute(0, 1, 2, 4, 3, 5).reshape(batch_size, channels, 2 * m, 2 * n) |
|
|
|
if extra_row or extra_col: |
|
x_expanded = torch.zeros(original_shape, dtype=x.dtype, device=x.device) |
|
x_expanded[:, :, :2 * m, :2 * n] = x |
|
if extra_row: |
|
x_expanded[:, :, -1:, :2 * n + 1] = extra_row_content |
|
if extra_col: |
|
x_expanded[:, :, :2 * m, -1:] = extra_col_content |
|
if extra_row and extra_col: |
|
x_expanded[:, :, -1:, -1:] = extra_col_content[:, :, -1:, :] |
|
x = x_expanded |
|
|
|
return x |
|
|
|
|
|
@torch.no_grad() |
|
def sample_euler_negative(model, x, sigmas, extra_args=None, callback=None, disable=None, s_churn=0., s_tmin=0., |
|
s_tmax=float('inf'), s_noise=1.): |
|
extra_args = {} if extra_args is None else extra_args |
|
s_in = x.new_ones([x.shape[0]]) |
|
for i in trange(len(sigmas) - 1, disable=disable): |
|
|
|
|
|
gamma = max(s_churn / (len(sigmas) - 1), 2 ** 0.5 - 1) if s_tmin <= sigmas[i] <= s_tmax else 0. |
|
eps = torch.randn_like(x) * s_noise |
|
sigma_hat = sigmas[i] * (gamma + 1) |
|
|
|
dt = sigmas[i + 1] - sigma_hat |
|
if gamma > 0: |
|
x = x - eps * (sigma_hat ** 2 - sigmas[i] ** 2) ** 0.5 |
|
denoised = model(x, sigma_hat * s_in, **extra_args) |
|
d = sampling.to_d(x, sigma_hat, denoised) |
|
if callback is not None: |
|
callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigma_hat, 'denoised': denoised}) |
|
|
|
if sigmas[i + 1] > 0 and i // 2 == 1: |
|
x = - x - d * dt |
|
else: |
|
x = x + d * dt |
|
return x |
|
|
|
|
|
|
|
|
|
if not NAME in [x.name for x in sd_samplers.all_samplers]: |
|
euler_max_samplers = [(NAME, sample_euler_negative, [ALIAS], {})] |
|
samplers_data_euler_max_samplers = [ |
|
sd_samplers_common.SamplerData(label, lambda model, funcname=funcname: sd_samplers_kdiffusion.KDiffusionSampler(funcname, model), aliases, options) |
|
for label, funcname, aliases, options in euler_max_samplers |
|
if callable(funcname) or hasattr(k_diffusion.sampling, funcname) |
|
] |
|
sd_samplers.all_samplers += samplers_data_euler_max_samplers |
|
sd_samplers.all_samplers_map = {x.name: x for x in sd_samplers.all_samplers} |
|
sd_samplers.set_samplers() |
|
|
