wan

Classes

fastvideo.configs.pipelines.wan.FastWan2_1_T2V_480P_Config dataclass

FastWan2_1_T2V_480P_Config(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 8.0, disable_autocast: bool = False, dit_config: DiTConfig = WanVideoConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = EncoderConfig(), image_encoder_precision: str = 'fp32', 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], Tensor], ...] = (lambda: (t5_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 = (lambda: [1000, 757, 522])(), ti2v_task: bool = False, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True)

Bases: WanT2V480PConfig

Base configuration for FastWan T2V 1.3B 480P pipeline architecture with DMD

fastvideo.configs.pipelines.wan.WANV2VConfig dataclass

WANV2VConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 3.0, disable_autocast: bool = False, dit_config: DiTConfig = WanVideoConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = WAN2_1ControlCLIPVisionConfig(), image_encoder_precision: str = 'bf16', 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], Tensor], ...] = (lambda: (t5_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, precision: str = 'bf16', warp_denoising_step: bool = True)

Bases: WanI2V480PConfig

Configuration for WAN2.1 1.3B Control pipeline.

fastvideo.configs.pipelines.wan.WanI2V480PConfig dataclass

WanI2V480PConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 3.0, disable_autocast: bool = False, dit_config: DiTConfig = WanVideoConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = CLIPVisionConfig(), image_encoder_precision: str = 'fp32', 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], Tensor], ...] = (lambda: (t5_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, precision: str = 'bf16', warp_denoising_step: bool = True)

Bases: WanT2V480PConfig

Base configuration for Wan I2V 14B 480P pipeline architecture.

fastvideo.configs.pipelines.wan.WanI2V720PConfig dataclass

WanI2V720PConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 5.0, disable_autocast: bool = False, dit_config: DiTConfig = WanVideoConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = CLIPVisionConfig(), image_encoder_precision: str = 'fp32', 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], Tensor], ...] = (lambda: (t5_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, precision: str = 'bf16', warp_denoising_step: bool = True)

Bases: WanI2V480PConfig

Base configuration for Wan I2V 14B 720P pipeline architecture.

fastvideo.configs.pipelines.wan.WanT2V480PConfig dataclass

WanT2V480PConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 3.0, disable_autocast: bool = False, dit_config: DiTConfig = WanVideoConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = EncoderConfig(), image_encoder_precision: str = 'fp32', 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], Tensor], ...] = (lambda: (t5_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, precision: str = 'bf16', warp_denoising_step: bool = True)

Bases: PipelineConfig

Base configuration for Wan T2V 1.3B pipeline architecture.

fastvideo.configs.pipelines.wan.WanT2V720PConfig dataclass

WanT2V720PConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 5.0, disable_autocast: bool = False, dit_config: DiTConfig = WanVideoConfig(), dit_precision: str = 'bf16', vae_config: VAEConfig = WanVAEConfig(), vae_precision: str = 'fp32', vae_tiling: bool = False, vae_sp: bool = False, image_encoder_config: EncoderConfig = EncoderConfig(), image_encoder_precision: str = 'fp32', 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], Tensor], ...] = (lambda: (t5_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, precision: str = 'bf16', warp_denoising_step: bool = True)

Bases: WanT2V480PConfig

Base configuration for Wan T2V 14B 720P pipeline architecture.