Files
hao-ai-lab-FastVideo/fastvideo/tests
Enderfga aa5ce59016 [feat] Add FlowMapEulerDiscreteScheduler
Standalone any-step Euler scheduler implementing AnyFlow's flow-map step
formula x_r = x_t - ((t - r) / num_train_timesteps) * u(x_t, t, r). Also
provides the AnyFlow training-time helpers apply_shift (flow-matching
shift transform), get_train_weight (per-timestep loss weight with
beta08 = t * sqrt(1-t) renormalized to num_train_timesteps total mass),
and add_noise (linear flow-matching interpolation).

Subclasses BaseScheduler so it slots into the existing FastVideo
scheduler discovery surface (timesteps/order/num_train_timesteps
attributes plus set_shift/set_timesteps/scale_model_input). Has no
diffusers ConfigMixin/SchedulerMixin dependency.

set_timesteps accepts custom_timesteps so configs can pin AnyFlow's
hand-tuned schedules (e.g. [999, 937, 833, 624, 0] for the 4-step
Wan2.1 setting from the paper).
2026-07-11 18:36:14 -07:00
..
2026-02-27 12:14:44 +08:00
2025-07-24 22:43:12 -07:00
2026-01-07 03:22:48 -08:00