mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2025-01-25 15:55:18 +00:00
Remove a bunch of useless code.
DDIM is the same as euler with a small difference in the inpaint code. DDIM uses randn_like but I set a fixed seed instead. I'm keeping it in because I'm sure if I remove it people are going to complain.
This commit is contained in:
comfyanonymous
parent
1777b54d02
commit
a268a574fa
@ -1,418 +0,0 @@
|
||||
"""SAMPLING ONLY."""
|
||||
|
||||
import torch
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
|
||||
from comfy.ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like, extract_into_tensor
|
||||
|
||||
|
||||
class DDIMSampler(object):
|
||||
def __init__(self, model, schedule="linear", device=torch.device("cuda"), **kwargs):
|
||||
super().__init__()
|
||||
self.model = model
|
||||
self.ddpm_num_timesteps = model.num_timesteps
|
||||
self.schedule = schedule
|
||||
self.device = device
|
||||
self.parameterization = kwargs.get("parameterization", "eps")
|
||||
|
||||
def register_buffer(self, name, attr):
|
||||
if type(attr) == torch.Tensor:
|
||||
if attr.device != self.device:
|
||||
attr = attr.float().to(self.device)
|
||||
setattr(self, name, attr)
|
||||
|
||||
def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True):
|
||||
ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps,
|
||||
num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose)
|
||||
self.make_schedule_timesteps(ddim_timesteps, ddim_eta=ddim_eta, verbose=verbose)
|
||||
|
||||
def make_schedule_timesteps(self, ddim_timesteps, ddim_eta=0., verbose=True):
|
||||
self.ddim_timesteps = torch.tensor(ddim_timesteps)
|
||||
alphas_cumprod = self.model.alphas_cumprod
|
||||
assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep'
|
||||
to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.device)
|
||||
|
||||
self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
|
||||
self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev))
|
||||
|
||||
# calculations for diffusion q(x_t | x_{t-1}) and others
|
||||
self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu())))
|
||||
self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu())))
|
||||
self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu())))
|
||||
self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu())))
|
||||
self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1)))
|
||||
|
||||
# ddim sampling parameters
|
||||
ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(),
|
||||
ddim_timesteps=self.ddim_timesteps,
|
||||
eta=ddim_eta,verbose=verbose)
|
||||
self.register_buffer('ddim_sigmas', ddim_sigmas)
|
||||
self.register_buffer('ddim_alphas', ddim_alphas)
|
||||
self.register_buffer('ddim_alphas_prev', ddim_alphas_prev)
|
||||
self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas))
|
||||
sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt(
|
||||
(1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * (
|
||||
1 - self.alphas_cumprod / self.alphas_cumprod_prev))
|
||||
self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps)
|
||||
|
||||
@torch.no_grad()
|
||||
def sample_custom(self,
|
||||
ddim_timesteps,
|
||||
conditioning=None,
|
||||
callback=None,
|
||||
img_callback=None,
|
||||
quantize_x0=False,
|
||||
eta=0.,
|
||||
mask=None,
|
||||
x0=None,
|
||||
temperature=1.,
|
||||
noise_dropout=0.,
|
||||
score_corrector=None,
|
||||
corrector_kwargs=None,
|
||||
verbose=True,
|
||||
x_T=None,
|
||||
log_every_t=100,
|
||||
unconditional_guidance_scale=1.,
|
||||
unconditional_conditioning=None, # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
|
||||
dynamic_threshold=None,
|
||||
ucg_schedule=None,
|
||||
denoise_function=None,
|
||||
extra_args=None,
|
||||
to_zero=True,
|
||||
end_step=None,
|
||||
disable_pbar=False,
|
||||
**kwargs
|
||||
):
|
||||
self.make_schedule_timesteps(ddim_timesteps=ddim_timesteps, ddim_eta=eta, verbose=verbose)
|
||||
samples, intermediates = self.ddim_sampling(conditioning, x_T.shape,
|
||||
callback=callback,
|
||||
img_callback=img_callback,
|
||||
quantize_denoised=quantize_x0,
|
||||
mask=mask, x0=x0,
|
||||
ddim_use_original_steps=False,
|
||||
noise_dropout=noise_dropout,
|
||||
temperature=temperature,
|
||||
score_corrector=score_corrector,
|
||||
corrector_kwargs=corrector_kwargs,
|
||||
x_T=x_T,
|
||||
log_every_t=log_every_t,
|
||||
unconditional_guidance_scale=unconditional_guidance_scale,
|
||||
unconditional_conditioning=unconditional_conditioning,
|
||||
dynamic_threshold=dynamic_threshold,
|
||||
ucg_schedule=ucg_schedule,
|
||||
denoise_function=denoise_function,
|
||||
extra_args=extra_args,
|
||||
to_zero=to_zero,
|
||||
end_step=end_step,
|
||||
disable_pbar=disable_pbar
|
||||
)
|
||||
return samples, intermediates
|
||||
|
||||
|
||||
@torch.no_grad()
|
||||
def sample(self,
|
||||
S,
|
||||
batch_size,
|
||||
shape,
|
||||
conditioning=None,
|
||||
callback=None,
|
||||
normals_sequence=None,
|
||||
img_callback=None,
|
||||
quantize_x0=False,
|
||||
eta=0.,
|
||||
mask=None,
|
||||
x0=None,
|
||||
temperature=1.,
|
||||
noise_dropout=0.,
|
||||
score_corrector=None,
|
||||
corrector_kwargs=None,
|
||||
verbose=True,
|
||||
x_T=None,
|
||||
log_every_t=100,
|
||||
unconditional_guidance_scale=1.,
|
||||
unconditional_conditioning=None, # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
|
||||
dynamic_threshold=None,
|
||||
ucg_schedule=None,
|
||||
**kwargs
|
||||
):
|
||||
if conditioning is not None:
|
||||
if isinstance(conditioning, dict):
|
||||
ctmp = conditioning[list(conditioning.keys())[0]]
|
||||
while isinstance(ctmp, list): ctmp = ctmp[0]
|
||||
cbs = ctmp.shape[0]
|
||||
if cbs != batch_size:
|
||||
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
|
||||
|
||||
elif isinstance(conditioning, list):
|
||||
for ctmp in conditioning:
|
||||
if ctmp.shape[0] != batch_size:
|
||||
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
|
||||
|
||||
else:
|
||||
if conditioning.shape[0] != batch_size:
|
||||
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
|
||||
|
||||
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
|
||||
# sampling
|
||||
C, H, W = shape
|
||||
size = (batch_size, C, H, W)
|
||||
print(f'Data shape for DDIM sampling is {size}, eta {eta}')
|
||||
|
||||
samples, intermediates = self.ddim_sampling(conditioning, size,
|
||||
callback=callback,
|
||||
img_callback=img_callback,
|
||||
quantize_denoised=quantize_x0,
|
||||
mask=mask, x0=x0,
|
||||
ddim_use_original_steps=False,
|
||||
noise_dropout=noise_dropout,
|
||||
temperature=temperature,
|
||||
score_corrector=score_corrector,
|
||||
corrector_kwargs=corrector_kwargs,
|
||||
x_T=x_T,
|
||||
log_every_t=log_every_t,
|
||||
unconditional_guidance_scale=unconditional_guidance_scale,
|
||||
unconditional_conditioning=unconditional_conditioning,
|
||||
dynamic_threshold=dynamic_threshold,
|
||||
ucg_schedule=ucg_schedule,
|
||||
denoise_function=None,
|
||||
extra_args=None
|
||||
)
|
||||
return samples, intermediates
|
||||
|
||||
def q_sample(self, x_start, t, noise=None):
|
||||
if noise is None:
|
||||
noise = torch.randn_like(x_start)
|
||||
return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
|
||||
extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
|
||||
|
||||
@torch.no_grad()
|
||||
def ddim_sampling(self, cond, shape,
|
||||
x_T=None, ddim_use_original_steps=False,
|
||||
callback=None, timesteps=None, quantize_denoised=False,
|
||||
mask=None, x0=None, img_callback=None, log_every_t=100,
|
||||
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
|
||||
unconditional_guidance_scale=1., unconditional_conditioning=None, dynamic_threshold=None,
|
||||
ucg_schedule=None, denoise_function=None, extra_args=None, to_zero=True, end_step=None, disable_pbar=False):
|
||||
device = self.model.alphas_cumprod.device
|
||||
b = shape[0]
|
||||
if x_T is None:
|
||||
img = torch.randn(shape, device=device)
|
||||
else:
|
||||
img = x_T
|
||||
|
||||
if timesteps is None:
|
||||
timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps
|
||||
elif timesteps is not None and not ddim_use_original_steps:
|
||||
subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1
|
||||
timesteps = self.ddim_timesteps[:subset_end]
|
||||
|
||||
intermediates = {'x_inter': [img], 'pred_x0': [img]}
|
||||
time_range = reversed(range(0,timesteps)) if ddim_use_original_steps else timesteps.flip(0)
|
||||
total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0]
|
||||
# print(f"Running DDIM Sampling with {total_steps} timesteps")
|
||||
|
||||
iterator = tqdm(time_range[:end_step], desc='DDIM Sampler', total=end_step, disable=disable_pbar)
|
||||
|
||||
for i, step in enumerate(iterator):
|
||||
index = total_steps - i - 1
|
||||
ts = torch.full((b,), step, device=device, dtype=torch.long)
|
||||
|
||||
if mask is not None:
|
||||
assert x0 is not None
|
||||
img_orig = self.q_sample(x0, ts) # TODO: deterministic forward pass?
|
||||
img = img_orig * mask + (1. - mask) * img
|
||||
|
||||
if ucg_schedule is not None:
|
||||
assert len(ucg_schedule) == len(time_range)
|
||||
unconditional_guidance_scale = ucg_schedule[i]
|
||||
|
||||
outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
|
||||
quantize_denoised=quantize_denoised, temperature=temperature,
|
||||
noise_dropout=noise_dropout, score_corrector=score_corrector,
|
||||
corrector_kwargs=corrector_kwargs,
|
||||
unconditional_guidance_scale=unconditional_guidance_scale,
|
||||
unconditional_conditioning=unconditional_conditioning,
|
||||
dynamic_threshold=dynamic_threshold, denoise_function=denoise_function, extra_args=extra_args)
|
||||
img, pred_x0 = outs
|
||||
if callback: callback(i)
|
||||
if img_callback: img_callback(pred_x0, i)
|
||||
|
||||
if index % log_every_t == 0 or index == total_steps - 1:
|
||||
intermediates['x_inter'].append(img)
|
||||
intermediates['pred_x0'].append(pred_x0)
|
||||
|
||||
if to_zero:
|
||||
img = pred_x0
|
||||
else:
|
||||
if ddim_use_original_steps:
|
||||
sqrt_alphas_cumprod = self.sqrt_alphas_cumprod
|
||||
else:
|
||||
sqrt_alphas_cumprod = torch.sqrt(self.ddim_alphas)
|
||||
img /= sqrt_alphas_cumprod[index - 1]
|
||||
|
||||
return img, intermediates
|
||||
|
||||
@torch.no_grad()
|
||||
def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
|
||||
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
|
||||
unconditional_guidance_scale=1., unconditional_conditioning=None,
|
||||
dynamic_threshold=None, denoise_function=None, extra_args=None):
|
||||
b, *_, device = *x.shape, x.device
|
||||
|
||||
if denoise_function is not None:
|
||||
model_output = denoise_function(x, t, **extra_args)
|
||||
elif unconditional_conditioning is None or unconditional_guidance_scale == 1.:
|
||||
model_output = self.model.apply_model(x, t, c)
|
||||
else:
|
||||
x_in = torch.cat([x] * 2)
|
||||
t_in = torch.cat([t] * 2)
|
||||
if isinstance(c, dict):
|
||||
assert isinstance(unconditional_conditioning, dict)
|
||||
c_in = dict()
|
||||
for k in c:
|
||||
if isinstance(c[k], list):
|
||||
c_in[k] = [torch.cat([
|
||||
unconditional_conditioning[k][i],
|
||||
c[k][i]]) for i in range(len(c[k]))]
|
||||
else:
|
||||
c_in[k] = torch.cat([
|
||||
unconditional_conditioning[k],
|
||||
c[k]])
|
||||
elif isinstance(c, list):
|
||||
c_in = list()
|
||||
assert isinstance(unconditional_conditioning, list)
|
||||
for i in range(len(c)):
|
||||
c_in.append(torch.cat([unconditional_conditioning[i], c[i]]))
|
||||
else:
|
||||
c_in = torch.cat([unconditional_conditioning, c])
|
||||
model_uncond, model_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
|
||||
model_output = model_uncond + unconditional_guidance_scale * (model_t - model_uncond)
|
||||
|
||||
if self.parameterization == "v":
|
||||
e_t = extract_into_tensor(self.sqrt_alphas_cumprod, t, x.shape) * model_output + extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x.shape) * x
|
||||
else:
|
||||
e_t = model_output
|
||||
|
||||
if score_corrector is not None:
|
||||
assert self.parameterization == "eps", 'not implemented'
|
||||
e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
|
||||
|
||||
alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
|
||||
alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
|
||||
sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
|
||||
sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
|
||||
# select parameters corresponding to the currently considered timestep
|
||||
a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
|
||||
a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
|
||||
sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
|
||||
sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
|
||||
|
||||
# current prediction for x_0
|
||||
if self.parameterization != "v":
|
||||
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
|
||||
else:
|
||||
pred_x0 = extract_into_tensor(self.sqrt_alphas_cumprod, t, x.shape) * x - extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x.shape) * model_output
|
||||
|
||||
if quantize_denoised:
|
||||
pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
|
||||
|
||||
if dynamic_threshold is not None:
|
||||
raise NotImplementedError()
|
||||
|
||||
# direction pointing to x_t
|
||||
dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
|
||||
noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
|
||||
if noise_dropout > 0.:
|
||||
noise = torch.nn.functional.dropout(noise, p=noise_dropout)
|
||||
x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
|
||||
return x_prev, pred_x0
|
||||
|
||||
@torch.no_grad()
|
||||
def encode(self, x0, c, t_enc, use_original_steps=False, return_intermediates=None,
|
||||
unconditional_guidance_scale=1.0, unconditional_conditioning=None, callback=None):
|
||||
num_reference_steps = self.ddpm_num_timesteps if use_original_steps else self.ddim_timesteps.shape[0]
|
||||
|
||||
assert t_enc <= num_reference_steps
|
||||
num_steps = t_enc
|
||||
|
||||
if use_original_steps:
|
||||
alphas_next = self.alphas_cumprod[:num_steps]
|
||||
alphas = self.alphas_cumprod_prev[:num_steps]
|
||||
else:
|
||||
alphas_next = self.ddim_alphas[:num_steps]
|
||||
alphas = torch.tensor(self.ddim_alphas_prev[:num_steps])
|
||||
|
||||
x_next = x0
|
||||
intermediates = []
|
||||
inter_steps = []
|
||||
for i in tqdm(range(num_steps), desc='Encoding Image'):
|
||||
t = torch.full((x0.shape[0],), i, device=self.model.device, dtype=torch.long)
|
||||
if unconditional_guidance_scale == 1.:
|
||||
noise_pred = self.model.apply_model(x_next, t, c)
|
||||
else:
|
||||
assert unconditional_conditioning is not None
|
||||
e_t_uncond, noise_pred = torch.chunk(
|
||||
self.model.apply_model(torch.cat((x_next, x_next)), torch.cat((t, t)),
|
||||
torch.cat((unconditional_conditioning, c))), 2)
|
||||
noise_pred = e_t_uncond + unconditional_guidance_scale * (noise_pred - e_t_uncond)
|
||||
|
||||
xt_weighted = (alphas_next[i] / alphas[i]).sqrt() * x_next
|
||||
weighted_noise_pred = alphas_next[i].sqrt() * (
|
||||
(1 / alphas_next[i] - 1).sqrt() - (1 / alphas[i] - 1).sqrt()) * noise_pred
|
||||
x_next = xt_weighted + weighted_noise_pred
|
||||
if return_intermediates and i % (
|
||||
num_steps // return_intermediates) == 0 and i < num_steps - 1:
|
||||
intermediates.append(x_next)
|
||||
inter_steps.append(i)
|
||||
elif return_intermediates and i >= num_steps - 2:
|
||||
intermediates.append(x_next)
|
||||
inter_steps.append(i)
|
||||
if callback: callback(i)
|
||||
|
||||
out = {'x_encoded': x_next, 'intermediate_steps': inter_steps}
|
||||
if return_intermediates:
|
||||
out.update({'intermediates': intermediates})
|
||||
return x_next, out
|
||||
|
||||
@torch.no_grad()
|
||||
def stochastic_encode(self, x0, t, use_original_steps=False, noise=None, max_denoise=False):
|
||||
# fast, but does not allow for exact reconstruction
|
||||
# t serves as an index to gather the correct alphas
|
||||
if use_original_steps:
|
||||
sqrt_alphas_cumprod = self.sqrt_alphas_cumprod
|
||||
sqrt_one_minus_alphas_cumprod = self.sqrt_one_minus_alphas_cumprod
|
||||
else:
|
||||
sqrt_alphas_cumprod = torch.sqrt(self.ddim_alphas)
|
||||
sqrt_one_minus_alphas_cumprod = self.ddim_sqrt_one_minus_alphas
|
||||
|
||||
if noise is None:
|
||||
noise = torch.randn_like(x0)
|
||||
if max_denoise:
|
||||
noise_multiplier = 1.0
|
||||
else:
|
||||
noise_multiplier = extract_into_tensor(sqrt_one_minus_alphas_cumprod, t, x0.shape)
|
||||
|
||||
return (extract_into_tensor(sqrt_alphas_cumprod, t, x0.shape) * x0 + noise_multiplier * noise)
|
||||
|
||||
@torch.no_grad()
|
||||
def decode(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None,
|
||||
use_original_steps=False, callback=None):
|
||||
|
||||
timesteps = np.arange(self.ddpm_num_timesteps) if use_original_steps else self.ddim_timesteps
|
||||
timesteps = timesteps[:t_start]
|
||||
|
||||
time_range = np.flip(timesteps)
|
||||
total_steps = timesteps.shape[0]
|
||||
print(f"Running DDIM Sampling with {total_steps} timesteps")
|
||||
|
||||
iterator = tqdm(time_range, desc='Decoding image', total=total_steps)
|
||||
x_dec = x_latent
|
||||
for i, step in enumerate(iterator):
|
||||
index = total_steps - i - 1
|
||||
ts = torch.full((x_latent.shape[0],), step, device=x_latent.device, dtype=torch.long)
|
||||
x_dec, _ = self.p_sample_ddim(x_dec, cond, ts, index=index, use_original_steps=use_original_steps,
|
||||
unconditional_guidance_scale=unconditional_guidance_scale,
|
||||
unconditional_conditioning=unconditional_conditioning)
|
||||
if callback: callback(i)
|
||||
return x_dec
|
||||
@ -1 +0,0 @@
|
||||
from .sampler import DPMSolverSampler
|
||||
File diff suppressed because it is too large
Load Diff
@ -1,96 +0,0 @@
|
||||
"""SAMPLING ONLY."""
|
||||
import torch
|
||||
|
||||
from .dpm_solver import NoiseScheduleVP, model_wrapper, DPM_Solver
|
||||
|
||||
MODEL_TYPES = {
|
||||
"eps": "noise",
|
||||
"v": "v"
|
||||
}
|
||||
|
||||
|
||||
class DPMSolverSampler(object):
|
||||
def __init__(self, model, device=torch.device("cuda"), **kwargs):
|
||||
super().__init__()
|
||||
self.model = model
|
||||
self.device = device
|
||||
to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device)
|
||||
self.register_buffer('alphas_cumprod', to_torch(model.alphas_cumprod))
|
||||
|
||||
def register_buffer(self, name, attr):
|
||||
if type(attr) == torch.Tensor:
|
||||
if attr.device != self.device:
|
||||
attr = attr.to(self.device)
|
||||
setattr(self, name, attr)
|
||||
|
||||
@torch.no_grad()
|
||||
def sample(self,
|
||||
S,
|
||||
batch_size,
|
||||
shape,
|
||||
conditioning=None,
|
||||
callback=None,
|
||||
normals_sequence=None,
|
||||
img_callback=None,
|
||||
quantize_x0=False,
|
||||
eta=0.,
|
||||
mask=None,
|
||||
x0=None,
|
||||
temperature=1.,
|
||||
noise_dropout=0.,
|
||||
score_corrector=None,
|
||||
corrector_kwargs=None,
|
||||
verbose=True,
|
||||
x_T=None,
|
||||
log_every_t=100,
|
||||
unconditional_guidance_scale=1.,
|
||||
unconditional_conditioning=None,
|
||||
# this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
|
||||
**kwargs
|
||||
):
|
||||
if conditioning is not None:
|
||||
if isinstance(conditioning, dict):
|
||||
ctmp = conditioning[list(conditioning.keys())[0]]
|
||||
while isinstance(ctmp, list): ctmp = ctmp[0]
|
||||
if isinstance(ctmp, torch.Tensor):
|
||||
cbs = ctmp.shape[0]
|
||||
if cbs != batch_size:
|
||||
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
|
||||
elif isinstance(conditioning, list):
|
||||
for ctmp in conditioning:
|
||||
if ctmp.shape[0] != batch_size:
|
||||
print(f"Warning: Got {ctmp.shape[0]} conditionings but batch-size is {batch_size}")
|
||||
else:
|
||||
if isinstance(conditioning, torch.Tensor):
|
||||
if conditioning.shape[0] != batch_size:
|
||||
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
|
||||
|
||||
# sampling
|
||||
C, H, W = shape
|
||||
size = (batch_size, C, H, W)
|
||||
|
||||
print(f'Data shape for DPM-Solver sampling is {size}, sampling steps {S}')
|
||||
|
||||
device = self.model.betas.device
|
||||
if x_T is None:
|
||||
img = torch.randn(size, device=device)
|
||||
else:
|
||||
img = x_T
|
||||
|
||||
ns = NoiseScheduleVP('discrete', alphas_cumprod=self.alphas_cumprod)
|
||||
|
||||
model_fn = model_wrapper(
|
||||
lambda x, t, c: self.model.apply_model(x, t, c),
|
||||
ns,
|
||||
model_type=MODEL_TYPES[self.model.parameterization],
|
||||
guidance_type="classifier-free",
|
||||
condition=conditioning,
|
||||
unconditional_condition=unconditional_conditioning,
|
||||
guidance_scale=unconditional_guidance_scale,
|
||||
)
|
||||
|
||||
dpm_solver = DPM_Solver(model_fn, ns, predict_x0=True, thresholding=False)
|
||||
x = dpm_solver.sample(img, steps=S, skip_type="time_uniform", method="multistep", order=2,
|
||||
lower_order_final=True)
|
||||
|
||||
return x.to(device), None
|
||||
@ -1,245 +0,0 @@
|
||||
"""SAMPLING ONLY."""
|
||||
|
||||
import torch
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
from functools import partial
|
||||
|
||||
from ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like
|
||||
from ldm.models.diffusion.sampling_util import norm_thresholding
|
||||
|
||||
|
||||
class PLMSSampler(object):
|
||||
def __init__(self, model, schedule="linear", device=torch.device("cuda"), **kwargs):
|
||||
super().__init__()
|
||||
self.model = model
|
||||
self.ddpm_num_timesteps = model.num_timesteps
|
||||
self.schedule = schedule
|
||||
self.device = device
|
||||
|
||||
def register_buffer(self, name, attr):
|
||||
if type(attr) == torch.Tensor:
|
||||
if attr.device != self.device:
|
||||
attr = attr.to(self.device)
|
||||
setattr(self, name, attr)
|
||||
|
||||
def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True):
|
||||
if ddim_eta != 0:
|
||||
raise ValueError('ddim_eta must be 0 for PLMS')
|
||||
self.ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps,
|
||||
num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose)
|
||||
alphas_cumprod = self.model.alphas_cumprod
|
||||
assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep'
|
||||
to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.model.device)
|
||||
|
||||
self.register_buffer('betas', to_torch(self.model.betas))
|
||||
self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
|
||||
self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev))
|
||||
|
||||
# calculations for diffusion q(x_t | x_{t-1}) and others
|
||||
self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu())))
|
||||
self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu())))
|
||||
self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu())))
|
||||
self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu())))
|
||||
self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1)))
|
||||
|
||||
# ddim sampling parameters
|
||||
ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(),
|
||||
ddim_timesteps=self.ddim_timesteps,
|
||||
eta=ddim_eta,verbose=verbose)
|
||||
self.register_buffer('ddim_sigmas', ddim_sigmas)
|
||||
self.register_buffer('ddim_alphas', ddim_alphas)
|
||||
self.register_buffer('ddim_alphas_prev', ddim_alphas_prev)
|
||||
self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas))
|
||||
sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt(
|
||||
(1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * (
|
||||
1 - self.alphas_cumprod / self.alphas_cumprod_prev))
|
||||
self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps)
|
||||
|
||||
@torch.no_grad()
|
||||
def sample(self,
|
||||
S,
|
||||
batch_size,
|
||||
shape,
|
||||
conditioning=None,
|
||||
callback=None,
|
||||
normals_sequence=None,
|
||||
img_callback=None,
|
||||
quantize_x0=False,
|
||||
eta=0.,
|
||||
mask=None,
|
||||
x0=None,
|
||||
temperature=1.,
|
||||
noise_dropout=0.,
|
||||
score_corrector=None,
|
||||
corrector_kwargs=None,
|
||||
verbose=True,
|
||||
x_T=None,
|
||||
log_every_t=100,
|
||||
unconditional_guidance_scale=1.,
|
||||
unconditional_conditioning=None,
|
||||
# this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
|
||||
dynamic_threshold=None,
|
||||
**kwargs
|
||||
):
|
||||
if conditioning is not None:
|
||||
if isinstance(conditioning, dict):
|
||||
cbs = conditioning[list(conditioning.keys())[0]].shape[0]
|
||||
if cbs != batch_size:
|
||||
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
|
||||
else:
|
||||
if conditioning.shape[0] != batch_size:
|
||||
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
|
||||
|
||||
self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
|
||||
# sampling
|
||||
C, H, W = shape
|
||||
size = (batch_size, C, H, W)
|
||||
print(f'Data shape for PLMS sampling is {size}')
|
||||
|
||||
samples, intermediates = self.plms_sampling(conditioning, size,
|
||||
callback=callback,
|
||||
img_callback=img_callback,
|
||||
quantize_denoised=quantize_x0,
|
||||
mask=mask, x0=x0,
|
||||
ddim_use_original_steps=False,
|
||||
noise_dropout=noise_dropout,
|
||||
temperature=temperature,
|
||||
score_corrector=score_corrector,
|
||||
corrector_kwargs=corrector_kwargs,
|
||||
x_T=x_T,
|
||||
log_every_t=log_every_t,
|
||||
unconditional_guidance_scale=unconditional_guidance_scale,
|
||||
unconditional_conditioning=unconditional_conditioning,
|
||||
dynamic_threshold=dynamic_threshold,
|
||||
)
|
||||
return samples, intermediates
|
||||
|
||||
@torch.no_grad()
|
||||
def plms_sampling(self, cond, shape,
|
||||
x_T=None, ddim_use_original_steps=False,
|
||||
callback=None, timesteps=None, quantize_denoised=False,
|
||||
mask=None, x0=None, img_callback=None, log_every_t=100,
|
||||
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
|
||||
unconditional_guidance_scale=1., unconditional_conditioning=None,
|
||||
dynamic_threshold=None):
|
||||
device = self.model.betas.device
|
||||
b = shape[0]
|
||||
if x_T is None:
|
||||
img = torch.randn(shape, device=device)
|
||||
else:
|
||||
img = x_T
|
||||
|
||||
if timesteps is None:
|
||||
timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps
|
||||
elif timesteps is not None and not ddim_use_original_steps:
|
||||
subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1
|
||||
timesteps = self.ddim_timesteps[:subset_end]
|
||||
|
||||
intermediates = {'x_inter': [img], 'pred_x0': [img]}
|
||||
time_range = list(reversed(range(0,timesteps))) if ddim_use_original_steps else np.flip(timesteps)
|
||||
total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0]
|
||||
print(f"Running PLMS Sampling with {total_steps} timesteps")
|
||||
|
||||
iterator = tqdm(time_range, desc='PLMS Sampler', total=total_steps)
|
||||
old_eps = []
|
||||
|
||||
for i, step in enumerate(iterator):
|
||||
index = total_steps - i - 1
|
||||
ts = torch.full((b,), step, device=device, dtype=torch.long)
|
||||
ts_next = torch.full((b,), time_range[min(i + 1, len(time_range) - 1)], device=device, dtype=torch.long)
|
||||
|
||||
if mask is not None:
|
||||
assert x0 is not None
|
||||
img_orig = self.model.q_sample(x0, ts) # TODO: deterministic forward pass?
|
||||
img = img_orig * mask + (1. - mask) * img
|
||||
|
||||
outs = self.p_sample_plms(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
|
||||
quantize_denoised=quantize_denoised, temperature=temperature,
|
||||
noise_dropout=noise_dropout, score_corrector=score_corrector,
|
||||
corrector_kwargs=corrector_kwargs,
|
||||
unconditional_guidance_scale=unconditional_guidance_scale,
|
||||
unconditional_conditioning=unconditional_conditioning,
|
||||
old_eps=old_eps, t_next=ts_next,
|
||||
dynamic_threshold=dynamic_threshold)
|
||||
img, pred_x0, e_t = outs
|
||||
old_eps.append(e_t)
|
||||
if len(old_eps) >= 4:
|
||||
old_eps.pop(0)
|
||||
if callback: callback(i)
|
||||
if img_callback: img_callback(pred_x0, i)
|
||||
|
||||
if index % log_every_t == 0 or index == total_steps - 1:
|
||||
intermediates['x_inter'].append(img)
|
||||
intermediates['pred_x0'].append(pred_x0)
|
||||
|
||||
return img, intermediates
|
||||
|
||||
@torch.no_grad()
|
||||
def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
|
||||
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
|
||||
unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None,
|
||||
dynamic_threshold=None):
|
||||
b, *_, device = *x.shape, x.device
|
||||
|
||||
def get_model_output(x, t):
|
||||
if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
|
||||
e_t = self.model.apply_model(x, t, c)
|
||||
else:
|
||||
x_in = torch.cat([x] * 2)
|
||||
t_in = torch.cat([t] * 2)
|
||||
c_in = torch.cat([unconditional_conditioning, c])
|
||||
e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
|
||||
e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
|
||||
|
||||
if score_corrector is not None:
|
||||
assert self.model.parameterization == "eps"
|
||||
e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
|
||||
|
||||
return e_t
|
||||
|
||||
alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
|
||||
alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
|
||||
sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
|
||||
sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
|
||||
|
||||
def get_x_prev_and_pred_x0(e_t, index):
|
||||
# select parameters corresponding to the currently considered timestep
|
||||
a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
|
||||
a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
|
||||
sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
|
||||
sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
|
||||
|
||||
# current prediction for x_0
|
||||
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
|
||||
if quantize_denoised:
|
||||
pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
|
||||
if dynamic_threshold is not None:
|
||||
pred_x0 = norm_thresholding(pred_x0, dynamic_threshold)
|
||||
# direction pointing to x_t
|
||||
dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
|
||||
noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
|
||||
if noise_dropout > 0.:
|
||||
noise = torch.nn.functional.dropout(noise, p=noise_dropout)
|
||||
x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
|
||||
return x_prev, pred_x0
|
||||
|
||||
e_t = get_model_output(x, t)
|
||||
if len(old_eps) == 0:
|
||||
# Pseudo Improved Euler (2nd order)
|
||||
x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t, index)
|
||||
e_t_next = get_model_output(x_prev, t_next)
|
||||
e_t_prime = (e_t + e_t_next) / 2
|
||||
elif len(old_eps) == 1:
|
||||
# 2nd order Pseudo Linear Multistep (Adams-Bashforth)
|
||||
e_t_prime = (3 * e_t - old_eps[-1]) / 2
|
||||
elif len(old_eps) == 2:
|
||||
# 3nd order Pseudo Linear Multistep (Adams-Bashforth)
|
||||
e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12
|
||||
elif len(old_eps) >= 3:
|
||||
# 4nd order Pseudo Linear Multistep (Adams-Bashforth)
|
||||
e_t_prime = (55 * e_t - 59 * old_eps[-1] + 37 * old_eps[-2] - 9 * old_eps[-3]) / 24
|
||||
|
||||
x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index)
|
||||
|
||||
return x_prev, pred_x0, e_t
|
||||
@ -1,22 +0,0 @@
|
||||
import torch
|
||||
import numpy as np
|
||||
|
||||
|
||||
def append_dims(x, target_dims):
|
||||
"""Appends dimensions to the end of a tensor until it has target_dims dimensions.
|
||||
From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusion/utils.py"""
|
||||
dims_to_append = target_dims - x.ndim
|
||||
if dims_to_append < 0:
|
||||
raise ValueError(f'input has {x.ndim} dims but target_dims is {target_dims}, which is less')
|
||||
return x[(...,) + (None,) * dims_to_append]
|
||||
|
||||
|
||||
def norm_thresholding(x0, value):
|
||||
s = append_dims(x0.pow(2).flatten(1).mean(1).sqrt().clamp(min=value), x0.ndim)
|
||||
return x0 * (value / s)
|
||||
|
||||
|
||||
def spatial_norm_thresholding(x0, value):
|
||||
# b c h w
|
||||
s = x0.pow(2).mean(1, keepdim=True).sqrt().clamp(min=value)
|
||||
return x0 * (value / s)
|
||||
@ -4,8 +4,6 @@ from .extra_samplers import uni_pc
|
||||
import torch
|
||||
import enum
|
||||
from comfy import model_management
|
||||
from .ldm.models.diffusion.ddim import DDIMSampler
|
||||
from .ldm.modules.diffusionmodules.util import make_ddim_timesteps
|
||||
import math
|
||||
from comfy import model_base
|
||||
import comfy.utils
|
||||
@ -511,41 +509,6 @@ class Sampler:
|
||||
sigma = float(sigmas[0])
|
||||
return math.isclose(max_sigma, sigma, rel_tol=1e-05) or sigma > max_sigma
|
||||
|
||||
class DDIM(Sampler):
|
||||
def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=None, denoise_mask=None, disable_pbar=False):
|
||||
timesteps = []
|
||||
for s in range(sigmas.shape[0]):
|
||||
timesteps.insert(0, model_wrap.sigma_to_discrete_timestep(sigmas[s]))
|
||||
noise_mask = None
|
||||
if denoise_mask is not None:
|
||||
noise_mask = 1.0 - denoise_mask
|
||||
|
||||
ddim_callback = None
|
||||
if callback is not None:
|
||||
total_steps = len(timesteps) - 1
|
||||
ddim_callback = lambda pred_x0, i: callback(i, pred_x0, None, total_steps)
|
||||
|
||||
max_denoise = self.max_denoise(model_wrap, sigmas)
|
||||
|
||||
ddim_sampler = DDIMSampler(model_wrap.inner_model.inner_model, device=noise.device)
|
||||
ddim_sampler.make_schedule_timesteps(ddim_timesteps=timesteps, verbose=False)
|
||||
z_enc = ddim_sampler.stochastic_encode(latent_image, torch.tensor([len(timesteps) - 1] * noise.shape[0]).to(noise.device), noise=noise, max_denoise=max_denoise)
|
||||
samples, _ = ddim_sampler.sample_custom(ddim_timesteps=timesteps,
|
||||
batch_size=noise.shape[0],
|
||||
shape=noise.shape[1:],
|
||||
verbose=False,
|
||||
eta=0.0,
|
||||
x_T=z_enc,
|
||||
x0=latent_image,
|
||||
img_callback=ddim_callback,
|
||||
denoise_function=model_wrap.predict_eps_discrete_timestep,
|
||||
extra_args=extra_args,
|
||||
mask=noise_mask,
|
||||
to_zero=sigmas[-1]==0,
|
||||
end_step=sigmas.shape[0] - 1,
|
||||
disable_pbar=disable_pbar)
|
||||
return samples
|
||||
|
||||
class UNIPC(Sampler):
|
||||
def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=None, denoise_mask=None, disable_pbar=False):
|
||||
return uni_pc.sample_unipc(model_wrap, noise, latent_image, sigmas, sampling_function=sampling_function, max_denoise=self.max_denoise(model_wrap, sigmas), extra_args=extra_args, noise_mask=denoise_mask, callback=callback, disable=disable_pbar)
|
||||
@ -558,13 +521,17 @@ KSAMPLER_NAMES = ["euler", "euler_ancestral", "heun", "dpm_2", "dpm_2_ancestral"
|
||||
"lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_sde", "dpmpp_sde_gpu",
|
||||
"dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm"]
|
||||
|
||||
def ksampler(sampler_name, extra_options={}):
|
||||
def ksampler(sampler_name, extra_options={}, inpaint_options={}):
|
||||
class KSAMPLER(Sampler):
|
||||
def sample(self, model_wrap, sigmas, extra_args, callback, noise, latent_image=None, denoise_mask=None, disable_pbar=False):
|
||||
extra_args["denoise_mask"] = denoise_mask
|
||||
model_k = KSamplerX0Inpaint(model_wrap)
|
||||
model_k.latent_image = latent_image
|
||||
model_k.noise = noise
|
||||
if inpaint_options.get("random", False): #TODO: Should this be the default?
|
||||
generator = torch.manual_seed(extra_args.get("seed", 41) + 1)
|
||||
model_k.noise = torch.randn(noise.shape, generator=generator, device="cpu").to(noise.dtype).to(noise.device)
|
||||
else:
|
||||
model_k.noise = noise
|
||||
|
||||
if self.max_denoise(model_wrap, sigmas):
|
||||
noise = noise * torch.sqrt(1.0 + sigmas[0] ** 2.0)
|
||||
@ -656,7 +623,7 @@ def sampler_class(name):
|
||||
elif name == "uni_pc_bh2":
|
||||
sampler = UNIPCBH2
|
||||
elif name == "ddim":
|
||||
sampler = DDIM
|
||||
sampler = ksampler("euler", inpaint_options={"random": True})
|
||||
else:
|
||||
sampler = ksampler(name)
|
||||
return sampler
|
||||
|
||||
Loading…
Reference in New Issue
Block a user