diffusers/pr_13921/en/api/schedulers/flow_match_heun_discrete.md

FlowMatchHeunDiscreteScheduler

FlowMatchHeunDiscreteScheduler is based on the flow-matching sampling introduced in EDM.

FlowMatchHeunDiscreteScheduler[[diffusers.FlowMatchHeunDiscreteScheduler]]

diffusers.FlowMatchHeunDiscreteScheduler[[diffusers.FlowMatchHeunDiscreteScheduler]]

Source

Heun scheduler.

This model inherits from SchedulerMixin and ConfigMixin. Check the superclass documentation for the generic methods the library implements for all schedulers such as loading and saving.

index_for_timestepdiffusers.FlowMatchHeunDiscreteScheduler.index_for_timestephttps://github.com/huggingface/diffusers/blob/vr_13921/src/diffusers/schedulers/scheduling_flow_match_heun_discrete.py#L179[{"name": "timestep", "val": ": float | torch.FloatTensor"}, {"name": "schedule_timesteps", "val": ": torch.FloatTensor | None = None"}]- timestep (float or torch.FloatTensor) -- The timestep value to find in the schedule.

• schedule_timesteps (torch.FloatTensor, optional) -- The timestep schedule to search in. If None, uses self.timesteps.0intThe index of the timestep in the schedule.

Find the index of a given timestep in the timestep schedule.

Parameters:

num_train_timesteps (int, defaults to 1000) : The number of diffusion steps to train the model.

shift (float, defaults to 1.0) : The shift value for the timestep schedule.

Returns:

int

The index of the timestep in the schedule.

scale_noise[[diffusers.FlowMatchHeunDiscreteScheduler.scale_noise]]

Source

Forward process in flow-matching

Parameters:

sample (torch.FloatTensor) : The input sample.

timestep (float or torch.FloatTensor) : The current timestep in the diffusion chain.

noise (torch.FloatTensor) : The noise tensor.

Returns:

torch.FloatTensor

A scaled input sample.

set_begin_index[[diffusers.FlowMatchHeunDiscreteScheduler.set_begin_index]]

Source

Sets the begin index for the scheduler. This function should be run from pipeline before the inference.

Parameters:

begin_index (int, defaults to 0) : The begin index for the scheduler.

set_timesteps[[diffusers.FlowMatchHeunDiscreteScheduler.set_timesteps]]

Source

Sets the discrete timesteps used for the diffusion chain (to be run before inference).

Parameters:

num_inference_steps (int) : The number of diffusion steps used when generating samples with a pre-trained model.

device (str or torch.device, optional) : The device to which the timesteps should be moved to. If None, the timesteps are not moved.

step[[diffusers.FlowMatchHeunDiscreteScheduler.step]]

Source

Predict the sample from the previous timestep by reversing the SDE. This function propagates the diffusion process from the learned model outputs (most often the predicted noise).

Parameters:

model_output (torch.FloatTensor) : The direct output from learned diffusion model.

timestep (float or torch.FloatTensor) : The current discrete timestep in the diffusion chain.

sample (torch.FloatTensor) : A current instance of a sample created by the diffusion process.

s_churn (float) : Stochasticity parameter that controls the amount of noise added during sampling. Higher values increase randomness.

s_tmin (float) : Minimum timestep threshold for applying stochasticity. Only timesteps above this value will have noise added.

s_tmax (float) : Maximum timestep threshold for applying stochasticity. Only timesteps below this value will have noise added.

s_noise (float, defaults to 1.0) : Scaling factor for noise added to the sample.

generator (torch.Generator, optional) : A random number generator.

return_dict (bool) : Whether or not to return a FlowMatchHeunDiscreteSchedulerOutput tuple.

Returns:

FlowMatchHeunDiscreteSchedulerOutput` or `tuple

If return_dict is True, FlowMatchHeunDiscreteSchedulerOutput is returned, otherwise a tuple is returned where the first element is the sample tensor.