Causal 3d convolusion.

`FlowDPMSolverMultistepScheduler` is a fast dedicated high-order solver for diffusion ODEs. This model inherits from [`SchedulerMixin`] and [

`UniPCMultistepScheduler` is a training-free framework designed for the fast sampling of diffusion models. This model inherits from [`Schedu

KPipeline is a language-aware support class with 2 main responsibilities: 1. Perform language-specific G2P, mapping (and chunking) text -> ph

Causal self-attention with a single head.

STFT/iSTFT without unfold/complex ops, using conv1d and conv_transpose1d. - forward STFT => Real-part conv1d + Imag-part conv1d - invers

KModel is a torch.nn.Module with 2 main responsibilities: 1. Init weights, downloading config.json + model.pth from HF if needed 2. forwa

Definition of sine generator SineGen(samp_rate, harmonic_num = 0, sine_amp = 0.1, noise_std = 0.003, voiced_threshold = 0

SourceModule for hn-nsf SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1, add_noise_std=0.003, voiced_threshod=0) sa

r""" Wan diffusion backbone supporting both text-to-video and image-to-video.

XLMRobertaModel with no pooler and no LM head.

r""" Wan diffusion backbone supporting both text-to-video and image-to-video.