stages ¶

def __init__(self, audio_decoder, vocoder) -> None:
    super().__init__()
    self.audio_decoder = audio_decoder
    self.vocoder = vocoder

def __init__(
    self,
    transformer,
    *,
    sigmas_override: list[float] | None = None,
    num_inference_steps_override: int | None = None,
    force_guidance_scale: float | None = None,
    initial_audio_latents_key: str | None = "ltx2_audio_latents",
) -> None:
    super().__init__()
    self.transformer = transformer
    self.sigmas_override = sigmas_override
    self.num_inference_steps_override = num_inference_steps_override
    self.force_guidance_scale = force_guidance_scale
    self.initial_audio_latents_key = initial_audio_latents_key

def __init__(self, transformer, vae) -> None:
    super().__init__()
    self.transformer = transformer
    self.vae = vae

def __init__(
    self,
    *,
    pipeline: Any,
    lora_path: str | None,
    lora_nickname: str = "ltx2_refine",
) -> None:
    super().__init__()
    self._pipeline_ref = (weakref.ref(pipeline) if pipeline is not None else None)
    self._lora_path = lora_path
    self._lora_nickname = lora_nickname
    self._applied = False

def __init__(self, text_encoders, tokenizers) -> None:
    """
    Initialize the prompt encoding stage.

    Args:
        enable_logging: Whether to enable logging for this stage.
        is_secondary: Whether this is a secondary text encoder.
    """
    super().__init__()
    self.tokenizers = tokenizers
    self.text_encoders = text_encoders
    self._last_audio_embeds: list[torch.Tensor] | None = None

def __init__(
    self,
    *,
    upsampler: Any,
    vae: Any,
    transformer: Any | None = None,
    sigmas: list[float] | None = None,
    add_noise: bool = True,
) -> None:
    super().__init__()
    self.upsampler = upsampler
    self.vae = vae
    self.transformer = transformer
    self.sigmas = sigmas or STAGE_2_DISTILLED_SIGMA_VALUES
    self.add_noise = add_noise