--- title: lingbotworld2 ---

fastvideo.configs.pipelines.lingbotworld2.DiTConfig

DiTConfig(arch_config: DiTArchConfig = DiTArchConfig(), prefix: str = '', quant_config: QuantizationConfig | None = None, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

fastvideo.configs.pipelines.lingbotworld2.DiTConfig.add_cli_args

add_cli_args(parser: Any, prefix: str = 'dit-config') -> Any

Add CLI arguments for DiTConfig fields

fastvideo.configs.pipelines.lingbotworld2.LingBotWorld2CausalFastVideoConfig

LingBotWorld2CausalFastVideoConfig(arch_config: DiTArchConfig = LingBotWorld2CausalFastArchConfig(), prefix: str = 'Wan', quant_config: QuantizationConfig | None = None, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

fastvideo.configs.pipelines.lingbotworld2.BaseEncoderOutput

BaseEncoderOutput(last_hidden_state: torch.FloatTensor | None = None, pooler_output: torch.FloatTensor | None = None, hidden_states: tuple[torch.FloatTensor, ...] | None = None, attentions: tuple[torch.FloatTensor, ...] | None = None, attention_mask: torch.Tensor | None = None)

fastvideo.configs.pipelines.lingbotworld2.LingBotWorld2UMT5Config

LingBotWorld2UMT5Config(arch_config: TextEncoderArchConfig = LingBotWorld2UMT5ArchConfig(), prefix: str = 'text_encoder', quant_config: QuantizationConfig | None = None, lora_config: Any | None = None, is_chat_model: bool = False, treat_empty_as_dot: bool = False, *, _resolved_attention_backend: AttentionBackendEnum | None = None, chat_template_enable_thinking: bool = False)

fastvideo.configs.pipelines.lingbotworld2.WanVAEConfig

WanVAEConfig(arch_config: WanVAEArchConfig = WanVAEArchConfig(), load_encoder: bool = True, load_decoder: bool = True, tile_sample_min_height: int = 256, tile_sample_min_width: int = 256, tile_sample_min_num_frames: int = 16, tile_sample_stride_height: int = 192, tile_sample_stride_width: int = 192, tile_sample_stride_num_frames: int = 12, blend_num_frames: int = 0, use_tiling: bool = False, use_temporal_tiling: bool = False, use_parallel_tiling: bool = False, use_temporal_scaling_frames: bool = True, use_feature_cache: bool = True, use_light_vae: bool = False, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

fastvideo.configs.pipelines.lingbotworld2.Wan2_2_I2V_A14B_Config

Wan2_2_I2V_A14B_Config(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 5.0, flow_shift_sr: float | None = None, disable_autocast: bool = False, scheduler_step_in_fp32: bool = False, is_causal: bool = False, dit_config: DiTConfig = WanVideoConfig(), dit_precision: str = 'bf16', upsampler_config: UpsamplerConfig = UpsamplerConfig(), upsampler_precision: str = 'fp32', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_decode_precision: str = 'bf16', 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: ('fp32',))(), preprocess_text_funcs: tuple[Callable[[str], str], ...] = (lambda: (preprocess_text,))(), postprocess_text_funcs: tuple[Callable[[BaseEncoderOutput], torch.Tensor], ...] = (lambda: (t5_postprocess_text,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = 0.9, precision: str = 'bf16', warp_denoising_step: bool = True)

fastvideo.configs.pipelines.lingbotworld2.lingbotworld2_whitespace_preprocess

lingbotworld2_whitespace_preprocess(prompt: str) -> str
Source
def lingbotworld2_whitespace_preprocess(prompt: str) -> str:
    text = ftfy.fix_text(prompt)
    text = html.unescape(html.unescape(text))
    return " ".join(text.strip().split())

fastvideo.configs.pipelines.lingbotworld2.lingbotworld2_t5_postprocess_text

lingbotworld2_t5_postprocess_text(outputs: BaseEncoderOutput) -> torch.Tensor
Source
def lingbotworld2_t5_postprocess_text(outputs: BaseEncoderOutput) -> torch.Tensor:
    assert outputs.last_hidden_state is not None
    return outputs.last_hidden_state

fastvideo.configs.pipelines.lingbotworld2.LingBotWorld2CausalFastI2V480PConfig

LingBotWorld2CausalFastI2V480PConfig(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 = LingBotWorld2CausalFastVideoConfig(), 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 = (lambda: (LingBotWorld2UMT5Config(),))(), 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)
Source
@dataclass
class LingBotWorld2CausalFastI2V480PConfig(Wan2_2_I2V_A14B_Config):
    dit_config: DiTConfig = field(default_factory=LingBotWorld2CausalFastVideoConfig)
    vae_config: WanVAEConfig = field(default_factory=WanVAEConfig)
    text_encoder_configs: tuple = field(default_factory=lambda: (LingBotWorld2UMT5Config(), ))
    preprocess_text_funcs: tuple = field(default_factory=lambda: (lingbotworld2_whitespace_preprocess, ))
    postprocess_text_funcs: tuple = field(default_factory=lambda: (lingbotworld2_t5_postprocess_text, ))
    text_encoder_precisions: tuple[str, ...] = field(default_factory=lambda: ("bf16", ))
    flow_shift: float | None = 10.0
    boundary_ratio: float | None = 0.947
    vae_precision: str = "fp32"
    vae_decode_precision: str | None = "fp32"
    vae_tiling: bool = False
    vae_sp: bool = False
    dit_precision: str = "bf16"
    is_causal: bool = False

    def __post_init__(self) -> None:
        self.vae_config.load_encoder = True
        self.vae_config.load_decoder = True