Dense LingBot-Video T2V pipeline configuration.

`fastvideo.configs.pipelines.lingbot_video.DiTConfig`

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

`fastvideo.configs.pipelines.lingbot_video.DiTConfig.add_cli_args`

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

Add CLI arguments for DiTConfig fields

`fastvideo.configs.pipelines.lingbot_video.EncoderConfig`

EncoderConfig(arch_config: ArchConfig = EncoderArchConfig(), prefix: str = '', quant_config: QuantizationConfig | None = None, lora_config: Any | None = None, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

`fastvideo.configs.pipelines.lingbot_video.VAEConfig`

VAEConfig(arch_config: VAEArchConfig = VAEArchConfig(), 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 = True, use_temporal_tiling: bool = True, use_parallel_tiling: bool = True, use_temporal_scaling_frames: bool = True, *, _resolved_attention_backend: AttentionBackendEnum | None = None)

`fastvideo.configs.pipelines.lingbot_video.VAEConfig.add_cli_args`

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

Add CLI arguments for VAEConfig fields

`fastvideo.configs.pipelines.lingbot_video.VAEConfig.from_cli_args`

from_cli_args(args: argparse.Namespace) -> VAEConfig

`fastvideo.configs.pipelines.lingbot_video.LingBotVideoConfig`

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

FastVideo component configuration for LingBot-Video transformers.

`fastvideo.configs.pipelines.lingbot_video.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.lingbot_video.LingBotVideoQwen3VLTextConfig`

LingBotVideoQwen3VLTextConfig(arch_config: TextEncoderArchConfig = LingBotVideoQwen3VLTextArchConfig(), prefix: str = 'language_model', 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 loader config for the LingBot-Video text-only Qwen3-VL path.

`fastvideo.configs.pipelines.lingbot_video.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.lingbot_video.PipelineConfig`

PipelineConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = None, flow_shift_sr: float | None = None, disable_autocast: bool = False, scheduler_step_in_fp32: bool = False, is_causal: bool = False, dit_config: DiTConfig = DiTConfig(), dit_precision: str = 'bf16', upsampler_config: UpsamplerConfig = UpsamplerConfig(), upsampler_precision: str = 'fp32', vae_config: VAEConfig = VAEConfig(), vae_precision: str = 'fp32', vae_decode_precision: str | None = None, vae_tiling: bool = True, vae_sp: bool = True, image_encoder_config: EncoderConfig = EncoderConfig(), 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: (EncoderConfig(),))(), 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: (postprocess_text,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None)

Base configuration for all pipeline architectures.

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.add_cli_args`

add_cli_args(parser: FlexibleArgumentParser, prefix: str = '') -> FlexibleArgumentParser

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.update_config_from_dict`

update_config_from_dict(args: dict[str, Any], prefix: str = '') -> None

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.from_pretrained`

from_pretrained(model_path: str) -> PipelineConfig

use the pipeline class setting from model_path to match the pipeline config

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.from_kwargs`

from_kwargs(kwargs: dict[str, Any], config_cli_prefix: str = '') -> PipelineConfig

Load PipelineConfig from kwargs Dictionary. kwargs: dictionary of kwargs config_cli_prefix: prefix of CLI arguments for this PipelineConfig instance

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.check_pipeline_config`

check_pipeline_config() -> None

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.resolve_checkpoint_settings`

resolve_checkpoint_settings(fastvideo_args: FastVideoArgs) -> None

Apply the run settings that the checkpoint at fastvideo_args.model_path fixes.

FastVideoArgs.__post_init__ calls this once in the main process, before argument validation and before any weights load. Most checkpoints fix no run settings, so the base implementation does nothing.

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.apply_request_constraints`

apply_request_constraints(request: GenerationRequest, sampling_param: SamplingParam) -> SamplingParam

Apply this model's constraints on a generation request to its sampling parameters.

sampling_param holds the preset defaults with the request's explicit fields applied. A model sets the values it fixes when the request leaves them unset, and raises when the request sets a value it does not accept. The base PipelineConfig accepts every request unchanged.

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.dump_to_json`

dump_to_json(file_path: str)

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.load_from_json`

load_from_json(file_path: str)

`fastvideo.configs.pipelines.lingbot_video.PipelineConfig.update_pipeline_config`

update_pipeline_config(source_pipeline_dict: dict[str, Any]) -> None

`fastvideo.configs.pipelines.lingbot_video.preprocess_lingbot_video_prompt`

preprocess_lingbot_video_prompt(prompt: str) -> str

Apply the released T2V system/user/assistant prompt template.

Source

def preprocess_lingbot_video_prompt(prompt: str) -> str:
    """Apply the released T2V system/user/assistant prompt template."""
    return PROMPT_TEMPLATE.format(prompt)

`fastvideo.configs.pipelines.lingbot_video.postprocess_lingbot_video_text`

postprocess_lingbot_video_text(outputs: BaseEncoderOutput, attention_mask: torch.Tensor) -> tuple[torch.Tensor, torch.Tensor]

Select the final hidden state, crop the template, and trim batch-one padding.

Source

def postprocess_lingbot_video_text(
    outputs: BaseEncoderOutput,
    attention_mask: torch.Tensor,
) -> tuple[torch.Tensor, torch.Tensor]:
    """Select the final hidden state, crop the template, and trim batch-one padding."""
    if outputs.hidden_states is None:
        raise ValueError("LingBot-Video requires text-encoder hidden states")
    prompt_embeds = outputs.hidden_states[-1][:, PROMPT_CROP_START:]
    prompt_mask = attention_mask[:, PROMPT_CROP_START:]
    if prompt_embeds.shape[0] == 1:
        true_length = int(prompt_mask[0].sum().item())
        prompt_embeds = prompt_embeds[:, :true_length]
        prompt_mask = prompt_mask[:, :true_length]
    return prompt_embeds, prompt_mask

`fastvideo.configs.pipelines.lingbot_video.LingBotVideoT2VConfig`

LingBotVideoT2VConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float | None = None, flow_shift: float | None = 3.0, flow_shift_sr: float | None = None, disable_autocast: bool = False, scheduler_step_in_fp32: bool = True, is_causal: bool = False, dit_config: DiTConfig = LingBotVideoConfig(), dit_precision: str = 'bf16', upsampler_config: UpsamplerConfig = UpsamplerConfig(), upsampler_precision: str = 'fp32', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_decode_precision: str | None = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = EncoderConfig(), 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: (LingBotVideoQwen3VLTextConfig(),))(), text_encoder_precisions: tuple[str, ...] = (lambda: ('bf16',))(), preprocess_text_funcs: tuple[Callable, ...] = (lambda: (preprocess_lingbot_video_prompt,))(), postprocess_text_funcs: tuple[Callable, ...] = (lambda: (postprocess_lingbot_video_text,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None)

Released Dense T2V component wiring and numerical precision policy.

Source

@dataclass
class LingBotVideoT2VConfig(PipelineConfig):
    """Released Dense T2V component wiring and numerical precision policy."""

    dit_config: DiTConfig = field(default_factory=LingBotVideoConfig)
    vae_config: VAEConfig = field(default_factory=WanVAEConfig)
    text_encoder_configs: tuple[EncoderConfig, ...] = field(default_factory=lambda: (LingBotVideoQwen3VLTextConfig(), ))
    preprocess_text_funcs: tuple[Callable, ...] = field(default_factory=lambda: (preprocess_lingbot_video_prompt, ))
    postprocess_text_funcs: tuple[Callable, ...] = field(default_factory=lambda: (postprocess_lingbot_video_text, ))
    text_encoder_precisions: tuple[str, ...] = field(default_factory=lambda: ("bf16", ))
    dit_precision: str = "bf16"
    vae_precision: str = "fp32"
    vae_decode_precision: str | None = "fp32"
    vae_tiling: bool = False
    vae_sp: bool = False
    flow_shift: float | None = 3.0
    embedded_cfg_scale: float | None = None
    scheduler_step_in_fp32: bool = True

    def __post_init__(self) -> None:
        """Load only the VAE decoder for the T2V workload."""
        self.vae_config.load_encoder = False
        self.vae_config.load_decoder = True