(file_path, torch_dtype=None)

(file_path, torch_dtype=None)

(self, model_paths)

(query, key, value, attn_bias=None)

()

()

()

()

()

()

(self, height, width, border_width)

(self, file_names_a, file_names_b)

(self, file_names_a, file_names_b)

(self, value, latents, masks, scales, blur_kernel_size=33, blur_sigma=10.0)

( dit: WanModel, x: torch.Tensor, timestep: torch.Tensor, context: torch.Tensor, tea_cache

( dit: WanModel, x: torch.Tensor, timestep: torch.Tensor, context: torch.Tensor, tea_cache

( dit: WanModel, x: torch.Tensor, timestep: torch.Tensor, context: torch.Tensor, tea_cache

(x, shift, scale)

(self, x, shift, scale)

(self, x, is_init_image=True)

(self, nnf, d)

(self)

(self)

(original_tensor, target_len)

(self, input_ids, image_sizes)

(fn)

(self, hidden_states)

(self, x: torch.Tensor)

(x: torch.Tensor, factor: int)

(x: torch.Tensor, factor: int)

(pos, seq_len)

(self, latents, post_normalize=True, contrast_enhance_scale=1.0)

(dim: int, end: int = 1024, theta: float = 10000.0)

(self, encoder_attention_mask, encoder_hidden_states, q_seqlen)

(n_frame, n_hw, dtype, device, batch_size=None)

(self, controlnet_image, masks, controlnet_inpaint_mask, tiler_kwargs, enable_controlnet_on_negative)

(self, control_video, num_frames, height, width, clip_feature=None, y=None, tiled=True, tile_size=(34, 34), ti

(self, prompt_emb_nega, eligen_entity_prompts, eligen_entity_masks, width, height, t5_sequence_length, enable_

(self, entity_prompts, entity_masks, width, height, t5_sequence_length=512, enable_eligen_inpaint=False)

(self, text_emb_t5, timestep, size_emb, dtype, batch_size)

(self, latents=None, guidance=1.0)

(self, latents)

(self, latents=None, guidance=1.0)

(self, latents=None, tiled=False, tile_size=64, tile_stride=32)

(self, latents=None)

(self, latents=None)

(self, latents, flex_inpaint_image=None, flex_inpaint_mask=None, flex_control_image=None, flex_control_strengt

(self, latents)

(self, latents)

(self, id_image, controlnet_image, infinityou_guidance, height, width)

(self, model, id_image, controlnet_image, infinityou_guidance, height, width)

(path: str, scale: float = 4, dtype=torch.bfloat16, device='cuda')

(path: str, scale: float = 4, dtype=torch.bfloat16, device='cuda')

(path: str, scale: int = 4, dtype=torch.bfloat16, device='cuda')

(path: str, scale: float = 4, dtype=torch.bfloat16, device='cuda')

(path: str, scale: int = 4, dtype=torch.bfloat16, device='cuda')

(path: str, scale: float = 4, dtype=torch.bfloat16, device='cuda')

(input_ids, image_inputs, past=None, **kwargs)

( self, input_ids: torch.LongTensor, past_key_values: Optional[torch.Tenso

(self, ipadapter_images, ipadapter_scale)

(self, images, height=384, width=384)

(self, input_image, height, width, seed, tiled, tile_size, tile_stride)

(self, motion_bucket_id)

(self, prompt, local_prompts, masks, mask_scales, t5_sequence_length, negative_prompt, cfg_scale)

(self, prompt, negative_prompt, image)

(self, text_emb, text_emb_t5, text_emb_mask, text_emb_mask_t5)

(self)

( self, latents, vace_video=None, vace_mask=None, vace_reference_image=None, vace_scal

(self, semantic_images, i2v_resolution="720p")

(self, masks, height, width, dim)

(self, hidden_states, image_rotary_emb, attn_mask=None, ipadapter_kwargs_list=None)

(self, image)

(self, image)

(self, image)

(self, images)

(self, hidden_states, to_qkv, norm_q, norm_k)

(self, q, k, v, image_rotary_emb, text_seq_length)

(self, source_guide, target_guide, source_style, target_style, nnf, err)

(self, heads)

( model_name, pretrained: str, repo_id: str, image_mean: Optional[Tuple[float, ...]] = None,

( model, tokenizer, model_config: Optional[dict], repo_id: str, commit_message: str = 'Add

(self, weight_bit_width: int)

(self, bits: int, empty_init=False, device=None, **kwargs)

(self, x)

(self, source_guide, target_guide, source_style, target_style, nnf, err)

(self, nnf, r)

(self)

(self, mu, log_var)

(self, alphas_cumprod)

(self, freqs_cis, x)

(self, input, size, interpolation="bicubic", align_corners=True)

(windows: torch.Tensor, win: Tuple[int, int, int], orig: Tuple[int, int, int])

(input, normalized_shape, eps=1e-6)

(self, pos: torch.Tensor, dim: int, theta: int)

(x)

(x)

(self, generator=None)