mirror of
https://github.com/Stability-AI/stablediffusion.git
synced 2024-12-23 08:04:59 +00:00
87 lines
No EOL
2.9 KiB
Python
87 lines
No EOL
2.9 KiB
Python
"""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, **kwargs):
|
|
super().__init__()
|
|
self.model = model
|
|
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 != torch.device("cuda"):
|
|
attr = attr.to(torch.device("cuda"))
|
|
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):
|
|
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}")
|
|
|
|
# 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 |