dew.diffusion.schedules.source
Published diffusion scheduler files, resolved once and sampled on their native grids.
Class defaults and solver controls live in source_policy; source_grids
builds the numerical tables without re-reading the config. SourceSchedule
keeps the public training and sampling contract and owns its grid cache.
| Name | Summary |
|---|---|
SourceGrid | A published pipeline’s sampling grid, prepared the way that pipeline prepares it: the scheduler file config (SourceSchedule.from_config) sampled at the latent token count tokens a resolution-dependent flow shift reads, its flow sigmas starting at origin (SourceSchedule.sampling). |
SourceSchedule | Reproduces a published scheduler file with Dew’s native solver and time grids. |
SourceGrid
Section titled “SourceGrid”class SourceGrid( config: Mapping[str, object], tokens: int | None = None, origin: Origin = 'scheduler',)A published pipeline’s sampling grid, prepared the way that pipeline prepares it: the
scheduler file config (SourceSchedule.from_config) sampled at the latent token count
tokens a resolution-dependent flow shift reads, its flow sigmas starting at origin
(SourceSchedule.sampling). Called with a step count, it returns the process and the explicit
descending grid that many steps sample on. Its fields are its record, so a run trained from
the pipeline saves the grid its samples are drawn on.
schedule: SourceSchedule-
The scheduler
confignames, read once, which keeps the grids it built.
SourceSchedule
Section titled “SourceSchedule”class SourceSchedule( config: Mapping[str, object], betas: np.ndarray, prediction: PredictionTransform, policy: SourcePolicy, solver: Solver, _grids: dict[tuple[int, int | None, Origin], tuple[Process, jax.Array]] = dict(),)Reproduces a published scheduler file with Dew’s native solver and time grids.
from_config reads the file’s class and controls once and resolves them
into a prediction transform, a native solver and the policy that
builds grids. It raises ValueError for an unsupported class or for an
active control this module does not reconstruct.
train_steps: int-
The training step count the class declares, which is the beta table’s length wherever the class tabulates one.
SourceSchedule.from_config
Section titled “SourceSchedule.from_config”def from_config(config: Mapping[str, object]) -> SourceScheduleSourceSchedule.training_process
Section titled “SourceSchedule.training_process”def training_process(tokens: int | None = None) -> ProcessReturn the process Dew fine-tunes the checkpoint on, at tokens latent tokens.
A scheduler file states how its checkpoint samples, so the training
process uses the convention its sampler reads. That is the VP beta
table, EDM’s log-normal sigma draw, or the flow path at the shift
its sampler uses. A file with dynamic shifting needs tokens. The
terminal stretch applies to sampling only.
SourceSchedule.sampling
Section titled “SourceSchedule.sampling”def sampling( steps: int, *, tokens: int | None = None, origin: Origin = 'scheduler',) -> tuple[Process, jax.Array]Return the process and the explicit descending grid for sampling in steps steps.
tokens is the latent token count that a resolution-dependent flow
shift reads, and origin is where a flow file’s sigmas start. The
calling pipeline supplies both through the task’s grid callable.
Raises ValueError when steps is not a positive integer, or when
it is larger than the training table of a tabulated or lambda
class.