LTX2T2VConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = None, disable_autocast: bool = False, is_causal: bool = False, dit_config: DiTConfig = LTX2VideoConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = LTX2VAEConfig(), vae_precision: str = 'bf16', vae_tiling: bool = True, vae_sp: bool = False, image_encoder_config: EncoderConfig = EncoderConfig(), image_encoder_precision: str = 'fp32', text_encoder_configs: tuple[EncoderConfig, ...] = (lambda: (LTX2GemmaConfig(),))(), text_encoder_precisions: tuple[str, ...] = (lambda: ('bf16',))(), preprocess_text_funcs: tuple[Callable[[str], str], ...] = (lambda: (preprocess_text,))(), postprocess_text_funcs: tuple[Callable[[BaseEncoderOutput], Tensor], ...] = (lambda: (ltx2_postprocess_text,))(), pos_magic: str | None = None, neg_magic: str | None = None, timesteps_scale: bool | None = None, mask_strategy_file_path: str | None = None, STA_mode: STA_Mode = STA_INFERENCE, skip_time_steps: int = 15, dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, boundary_ratio: float | None = None, audio_decoder_config: ModelConfig = LTX2AudioDecoderConfig(), vocoder_config: ModelConfig = LTX2VocoderConfig(), audio_decoder_precision: str = 'bf16', vocoder_precision: str = 'bf16')
Bases: PipelineConfig
Configuration for LTX-2 T2V pipeline.