diff options
Diffstat (limited to 'modules/models/diffusion/uni_pc')
| -rw-r--r-- | modules/models/diffusion/uni_pc/__init__.py | 2 | ||||
| -rw-r--r-- | modules/models/diffusion/uni_pc/sampler.py | 3 | ||||
| -rw-r--r-- | modules/models/diffusion/uni_pc/uni_pc.py | 16 |
3 files changed, 12 insertions, 9 deletions
diff --git a/modules/models/diffusion/uni_pc/__init__.py b/modules/models/diffusion/uni_pc/__init__.py index e1265e3f..dbb35964 100644 --- a/modules/models/diffusion/uni_pc/__init__.py +++ b/modules/models/diffusion/uni_pc/__init__.py @@ -1 +1 @@ -from .sampler import UniPCSampler +from .sampler import UniPCSampler # noqa: F401 diff --git a/modules/models/diffusion/uni_pc/sampler.py b/modules/models/diffusion/uni_pc/sampler.py index a241c8a7..0a9defa1 100644 --- a/modules/models/diffusion/uni_pc/sampler.py +++ b/modules/models/diffusion/uni_pc/sampler.py @@ -54,7 +54,8 @@ class UniPCSampler(object): if conditioning is not None: if isinstance(conditioning, dict): ctmp = conditioning[list(conditioning.keys())[0]] - while isinstance(ctmp, list): ctmp = ctmp[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}") diff --git a/modules/models/diffusion/uni_pc/uni_pc.py b/modules/models/diffusion/uni_pc/uni_pc.py index 1d1b07bd..d257a728 100644 --- a/modules/models/diffusion/uni_pc/uni_pc.py +++ b/modules/models/diffusion/uni_pc/uni_pc.py @@ -1,5 +1,4 @@ import torch -import torch.nn.functional as F import math import tqdm @@ -94,7 +93,7 @@ class NoiseScheduleVP: """ if schedule not in ['discrete', 'linear', 'cosine']: - raise ValueError("Unsupported noise schedule {}. The schedule needs to be 'discrete' or 'linear' or 'cosine'".format(schedule)) + raise ValueError(f"Unsupported noise schedule {schedule}. The schedule needs to be 'discrete' or 'linear' or 'cosine'") self.schedule = schedule if schedule == 'discrete': @@ -179,13 +178,13 @@ def model_wrapper( model, noise_schedule, model_type="noise", - model_kwargs={}, + model_kwargs=None, guidance_type="uncond", #condition=None, #unconditional_condition=None, guidance_scale=1., classifier_fn=None, - classifier_kwargs={}, + classifier_kwargs=None, ): """Create a wrapper function for the noise prediction model. @@ -276,6 +275,9 @@ def model_wrapper( A noise prediction model that accepts the noised data and the continuous time as the inputs. """ + model_kwargs = model_kwargs or {} + classifier_kwargs = classifier_kwargs or {} + def get_model_input_time(t_continuous): """ Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time. @@ -342,7 +344,7 @@ def model_wrapper( t_in = torch.cat([t_continuous] * 2) if isinstance(condition, dict): assert isinstance(unconditional_condition, dict) - c_in = dict() + c_in = {} for k in condition: if isinstance(condition[k], list): c_in[k] = [torch.cat([ @@ -353,7 +355,7 @@ def model_wrapper( unconditional_condition[k], condition[k]]) elif isinstance(condition, list): - c_in = list() + c_in = [] assert isinstance(unconditional_condition, list) for i in range(len(condition)): c_in.append(torch.cat([unconditional_condition[i], condition[i]])) @@ -469,7 +471,7 @@ class UniPC: t = torch.linspace(t_T**(1. / t_order), t_0**(1. / t_order), N + 1).pow(t_order).to(device) return t else: - raise ValueError("Unsupported skip_type {}, need to be 'logSNR' or 'time_uniform' or 'time_quadratic'".format(skip_type)) + raise ValueError(f"Unsupported skip_type {skip_type}, need to be 'logSNR' or 'time_uniform' or 'time_quadratic'") def get_orders_and_timesteps_for_singlestep_solver(self, steps, order, skip_type, t_T, t_0, device): """ |