Classes¶
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, 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_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,))(), dmd_denoising_steps: list[int] | None = (lambda: [1000, 757, 522])(), ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True)
dataclass
¶
LucyEditDevConfig(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 = (lambda: WanVideoConfig(arch_config=WanVideoArchConfig(num_attention_heads=24, in_channels=96, out_channels=48, ffn_dim=14336, num_layers=30)))(), dit_precision: str = 'bf16', upsampler_config: UpsamplerConfig = UpsamplerConfig(), upsampler_precision: str = 'fp32', vae_config: VAEConfig = (lambda: WanVAEConfig(arch_config=WanVAEArchConfig(base_dim=160, decoder_base_dim=256, z_dim=48, in_channels=12, out_channels=12, scale_factor_spatial=16, patch_size=2, is_residual=True, clip_output=False, latents_mean=(-0.2289, -0.0052, -0.1323, -0.2339, -0.2799, 0.0174, 0.1838, 0.1557, -0.1382, 0.0542, 0.2813, 0.0891, 0.157, -0.0098, 0.0375, -0.1825, -0.2246, -0.1207, -0.0698, 0.5109, 0.2665, -0.2108, -0.2158, 0.2502, -0.2055, -0.0322, 0.1109, 0.1567, -0.0729, 0.0899, -0.2799, -0.123, -0.0313, -0.1649, 0.0117, 0.0723, -0.2839, -0.2083, -0.052, 0.3748, 0.0152, 0.1957, 0.1433, -0.2944, 0.3573, -0.0548, -0.1681, -0.0667), latents_std=(0.4765, 1.0364, 0.4514, 1.1677, 0.5313, 0.499, 0.4818, 0.5013, 0.8158, 1.0344, 0.5894, 1.0901, 0.6885, 0.6165, 0.8454, 0.4978, 0.5759, 0.3523, 0.7135, 0.6804, 0.5833, 1.4146, 0.8986, 0.5659, 0.7069, 0.5338, 0.4889, 0.4917, 0.4069, 0.4999, 0.6866, 0.4093, 0.5709, 0.6065, 0.6415, 0.4944, 0.5726, 1.2042, 0.5458, 1.6887, 0.3971, 1.06, 0.3943, 0.5537, 0.5444, 0.4089, 0.7468, 0.7744))))(), 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,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = True, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True, expand_timesteps: bool = True)
Bases: Wan2_2_TI2V_5B_Config
Configuration for Decart Lucy Edit Dev video editing.
dataclass
¶
WANV2VConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 3.0, 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_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,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True)
dataclass
¶
WanI2V480PConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 3.0, 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_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,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True)
dataclass
¶
WanI2V720PConfig(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_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,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True)
dataclass
¶
WanT2V480PConfig(model_path: str = '', pipeline_config_path: str | None = None, embedded_cfg_scale: float = 6.0, flow_shift: float | None = 3.0, 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_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,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True)
dataclass
¶
WanT2V720PConfig(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_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,))(), dmd_denoising_steps: list[int] | None = None, ti2v_task: bool = False, lucy_edit_task: bool = False, boundary_ratio: float | None = None, precision: str = 'bf16', warp_denoising_step: bool = True)