(poses: list[list[float]], RT: np.ndarray)

(self)

(self)

(self)

(self)

(self, multival: Union[float, Tensor])

(self, FLOAT: Union[float, list[float]])

(self, noise_type: str, seed_offset: int, determinism: str=NoiseDeterminism.DEFAULT, seed_override: int=None)

(self, start_percent=0.0, end_percent=0.1, weighted_mean=0.95, strength_multival: Union[float, Tensor]=None,

(self, start_percent=0.0, end_percent=0.1, strength_multival: Union[float, Tensor]=None,

(self)

(self, sliding_width)

(self, switch_on_idxs: str, always_include_0: bool)

(self, attn_style_fidelity=1.0, attn_ref_weight=1.0, attn_strength=1.0, adain_style_fi

(self, attn_style_fidelity=1.0, attn_ref_weight=1.0, attn_strength=1.0)

(self, cfg: float, cfg_extras: CFGExtrasGroup=None)

(self, cfg_multival: Union[float, Tensor], start_percent: float=0.0, guarantee_steps: int=1,

(self, cfg: float, start_percent: float=0.0, guarantee_steps: int=1, prev_custom_cfg

(self, start_percent: float, end_percent: float, cfg_start

(self, cfgs_float: Union[float, list[float]], start_percent: float, end_percent:

(self)

(self, strength_model: float, start_percent: float, guarantee_steps: float, prev_

(self, start_percent: float, end_percent: float, s

(self, strengths_float: Union[float, list[float]], start_percent: float, end_per

(self, image: Tensor, vae: VAE, invert_mask: bool, resize_image: bool, start_percent: float,

(self, x=0, y=0)

(self, iterations: int, iter_batch_offset: int=0, iter_seed_offset: int=0)

(self, iterations: int, filter: str, d_s: float, d_t: float, n_butterworth: int, sigm

(self, prev_kf=None, mult=1.0, mult_multival=None, start_percent=0.0, guarantee_steps=

(self, start_percent: float, end_percent: float, mult_start: f

(self, mults_float: Union[float, list[float]], start_percent: float, end_percent: floa

(self, prev_kf: ContextRefKeyframeGroup=None, mult=1.0, mult_multival=None, mode_repla

(self, start_percent: float, end_percent: float, mult_start: f

(self, mults_float: Union[float, list[float]], start_percent: float, end_percent: floa

(self, batch_offset: int, noise_type: str, seed_gen_override: str, seed_offset: int, pre

(self, batch_offset: int, noise_type: str, seed_gen_override: str, seed_offset: int, noi

(self, batch_offset: int, noise_type: str, seed_gen_override: str, seed_offset: int, noi

(self, batch_offset: int, noise_type: str, seed_gen_override: str, seed_offset: int, noi

(self)

(self, float_val: Union[float, list[float]]=1.0, mask_optional: Tensor=None)

(self, min_float_val: float, max_float_val: float, mask: Tensor, scaling: str=ScaleType.ABSOLUTE)

(self, float_val: Union[float, list[float]]=None, mask_optional: Tensor=None)

(self, floats: Union[float, list[float]]=None, mask_optional: Tensor=None)

(self, calib_iterations: int, thresh_freq: float)

(self, context_length: int, context_stride: int, context_overlap: int, closed_loop: bool,

(self, fuse_method: str=ContextFuseMethod.FLAT, context_schedule: str=None, **kwargs)

(self, context_length: int, context_stride: int, context_overlap: int, fuse_method: str

(self, context_length: int, context_overlap: int, fuse_method: str=ContextFuseMethod.PY

(self, context_length: int, start_percent: float=0.0, guarantee_steps: int=1, prev_cont

(self, view_length: int, view_overlap: int, fuse_method: str=ContextFuseMethod.FLAT,)

(self, view_length: int, view_overlap: int, view_stride: int, fuse_method: str=ContextF

(self, view_length: int, view_overlap: int, view_stride: int, closed_loop: bool, fuse_m

(self, down_0: Union[ADBlockHolder, None]=None, down_1: Unio

(self, down_0__0: Union[ADBlockHolder, None]=None, down_0__1

(self, effect_21_floats: Union[list[float], None]=None, scal

(self, down_0: Union[ADBlockHolder, None]=None, down_1: Unio

(self, down_0__0: Union[ADBlockHolder, None]=None, down_0__1

(self, effect_16_floats: Union[list[float], None]=None, scal

(self, multival: Union[float, Tensor], effect_multival: Union[float, Tensor]=None)

(self, preset: str, batch_index: int, mult_multival: Union[float, Tensor]=None, print_values: bool=False, effe

(self, prompts: str, clip, latent: dict, print_schedule=False, tensor_interp=TensorInterp.LERP,

(self, prompts: str, clip, print_schedule=False, max_length: int=0, tensor_interp=TensorInterp.LERP,

(self, values: str, latent: dict, print_schedule=False)

(self, values: str, max_length: int, print_schedule=False)

(self, start_percent: float, end_percent: float)

(self, batch_offset: int, noise_type: str, seed_gen: str, seed_offset: int, noise_layers: NoiseLayerGroup=None

(length: int, **kwargs)

(length: int, **kwargs)

(length: int, **kwargs)

(length: int, **kwargs)

(length: int, full_length: int, idxs: list[int], ctx_opts: ContextOptions, **kwargs)

(length: int, **kwargs)

(length: int, **kwargs)

(length: int, **kwargs)

(length: int, **kwargs)

(num_frames: int, opts: Union[ContextOptionsGroup, ContextOptions])

(num_frames: int, opts: Union[ContextOptionsGroup, ContextOptions])

(num_frames: int, opts: Union[ContextOptionsGroup, ContextOptions])

(num_frames: int, opts: Union[ContextOptionsGroup, ContextOptions])

(num_frames: int, opts: Union[ContextOptionsGroup, ContextOptions])

(self)

(x: Tensor, seed: int=None)

(self, model: ModelPatcher)

(patcher: ModelPatcher)

(args)

(model, x: Tensor, timestep: Tensor, uncond, cond, cond_scale, model_options: dict={}, seed=None)

(self)

(self, conditioning, index: int=0)

(nodes)

(self, sample)

(self, x: Tensor, video_length: int, batched_number: int)

(self, x: Tensor)

(self, x: Tensor)

(self, input_tensor: Tensor, encoder_hidden_states=None, attention_mask=None, transformer_options=None)

(self, hidden_states, encoder_hidden_states=None, attention_mask=None, view_options: ContextOptions=None, mm_k

( self, hidden_states: Tensor, encoder_hidden_states: Tensor=None, attention_m

( self, hidden_states: Tensor, encoder_hidden_states=None, attention_mask=None

(self, input_tensor: Tensor, encoder_hidden_states=None, attention_mask=None, transformer_options=None)

(self, x, context=None, value=None, mask=None, scale_mask=None, mm_kwargs=None, transformer_options=None)