mmagic.models.diffusion_schedulers.ddpm_scheduler

Module Contents

Classes

EditDDPMScheduler

class mmagic.models.diffusion_schedulers.ddpm_scheduler.EditDDPMScheduler(num_train_timesteps: int = 1000, beta_start: float = 0.0001, beta_end: float = 0.02, beta_schedule: str = 'linear', trained_betas: Optional[Union[numpy.array, list]] = None, variance_type='fixed_small', clip_sample=True)

set_timesteps(num_inference_steps)

set timesteps.

_get_variance(t, predicted_variance=None, variance_type=None)

get variance.

step(model_output: torch.FloatTensor, timestep: int, sample: torch.FloatTensor, predict_epsilon=True, cond_fn=None, cond_kwargs={}, generator=None)

add_noise(original_samples, noise, timesteps)

add noise.

abstract training_loss(model, x_0, t)

abstract sample_timestep()

__len__()