Buckets:

|
download
raw
4.54 kB

PiflowScheduler

PiflowScheduler is the few-step scheduler of the distilled Kandinsky 6 checkpoints, both the text/image-to-video-and-audio model and the video super-resolution model. It implements π-Flow: the transformer predicts n_grid denoised estimates per latent channel at a small number of grid points, and the scheduler integrates a network-free policy between them.

The reference implementation can be found at Lakonik/LakonLab.

PiflowScheduler[[diffusers.PiflowScheduler]]

diffusers.PiflowScheduler[[diffusers.PiflowScheduler]]

diffusers.PiflowScheduler(num_train_timesteps: int = 1000, shift: float = 5.0, n_grid: int = 10, eps: float = 1e-06, final_step_size_scale: float = 0.5, num_policy_substeps: int = 128)

Source

Parameters:

num_train_timesteps (int, optional, defaults to 1000) : Number of training diffusion steps.

shift (float, optional, defaults to 5.0) : Flow-matching timestep shift.

n_grid (int, optional, defaults to 10) : Number of predictions in the widened model output.

eps (float, optional, defaults to 1e-6) : Minimum timestep and policy denominator.

final_step_size_scale (float, optional, defaults to 0.5) : Relative size of the final raw-timestep segment.

num_policy_substeps (int, optional, defaults to 128) : Maximum policy integration substeps per raw-timestep unit.

Few-step PiFlow scheduler for widened-output diffusion transformers.

PiFlow evaluates the denoising model at a small number of grid points and integrates a network-free policy between those evaluations. The scheduler is intended for distilled Kandinsky 6 checkpoints, including the main video/audio model and the video super-resolution model. Their model output contains n_grid predictions per sample channel.

This scheduler inherits from SchedulerMixin and ConfigMixin. Check the superclass documentation for the generic methods implemented for all schedulers (loading, saving, etc.).

set_timesteps[[diffusers.PiflowScheduler.set_timesteps]]

set_timesteps(num_inference_steps: int | None = None, device: typing.Union[str, torch.device, NoneType] = None, sigmas: list[float] | None = None, mu: float | None = None, timesteps: list[float] | None = None)

Source

Parameters:

num_inference_steps (int) : Number of model evaluations.

device (str or torch.device, optional) : Device for the schedule.

sigmas (list[float], optional) : Unsupported custom sigma schedule.

mu (float, optional) : Unsupported dynamic-shift parameter.

timesteps (list[float], optional) : Unsupported custom timestep schedule.

Set the distilled PiFlow timestep schedule.

step[[diffusers.PiflowScheduler.step]]

step(model_output: FloatTensor, timestep: typing.Union[float, torch.FloatTensor], sample: FloatTensor, return_dict: bool = True)

Source

Parameters:

model_output (torch.FloatTensor) : Widened model output containing n_grid predictions per sample channel.

timestep (float or torch.FloatTensor) : Current scheduler timestep.

sample (torch.FloatTensor) : Current noisy sample.

return_dict (bool, optional, defaults to True) : Whether to return a [PiflowSchedulerOutput].

Returns: [PiflowSchedulerOutput] or tuple

Updated sample.

Advance one step by integrating the PiFlow policy.

PiflowSchedulerOutput[[diffusers.schedulers.scheduling_piflow.PiflowSchedulerOutput]]

diffusers.schedulers.scheduling_piflow.PiflowSchedulerOutput[[diffusers.schedulers.scheduling_piflow.PiflowSchedulerOutput]]

diffusers.schedulers.scheduling_piflow.PiflowSchedulerOutput(prev_sample: Tensor)

Source

Parameters:

prev_sample (torch.Tensor) : Computed sample at the next PiFlow grid point. Should be used as the next denoising input.

Output class for the scheduler's step function output.

Xet Storage Details

Size:
4.54 kB
·
Xet hash:
5809486f2e73eed51153e89f3c6e0e212a85202fc41fc4a1ba21e21ba9b390d7

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.