lingbotworld_fast ¶
Classes¶
fastvideo.configs.pipelines.lingbotworld_fast.LingBotWorldFastI2V480PConfig dataclass ¶
LingBotWorldFastI2V480PConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 10.0, flow_shift_sr: float | None = None, disable_autocast: bool = False, scheduler_step_in_fp32: bool = False, is_causal: bool = False, dit_config: DiTConfig = LingBotWorldFastVideoConfig(), dit_precision: str = 'bf16', upsampler_config: UpsamplerConfig = UpsamplerConfig(), upsampler_precision: str = 'fp32', vae_config: WanVAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_decode_precision: str | None = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = CLIPVisionConfig(), image_encoder_precision: str = 'fp32', image_encoder_configs: tuple[EncoderConfig, ...] | None = None, image_encoder_precisions: tuple[str, ...] | None = None, text_encoder_configs: tuple[EncoderConfig, ...] = (lambda: (T5Config(),))(), text_encoder_precisions: tuple[str, ...] = (lambda: ('bf16',))(), preprocess_text_funcs: tuple = (lambda: (lingbotworld2_whitespace_preprocess,))(), postprocess_text_funcs: tuple = (lambda: (lingbotworld2_t5_postprocess_text,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = 0.947, precision: str = 'bf16', warp_denoising_step: bool = True)
Bases: LingBotWorld2CausalFastI2V480PConfig
Pipeline config for LingBot-World-Fast 480P image-to-video.
Shares the LingBot World 2 causal-fast sampling loop and Wan VAE, but this checkpoint ships the stock UMT5EncoderModel text encoder (d_model fields) rather than LingBot World 2's custom one (dim fields), so the standard T5Config is restored here alongside this DiT's arch config.