MCPcopy Create free account

hub / github.com/bytedance/DreamID-V / functions

Functions524 in github.com/bytedance/DreamID-V

⨍ Functions 524◇ Types & classes 122
↓ 1 callersMethodmultistep_uni_c_bh_update
One step for the UniC (B(h) version). Args: this_model_output (`torch.Tensor`): The model outputs at `x_
dreamidv_wan/utils/fm_solvers_unipc.py:486
↓ 1 callersMethodmultistep_uni_p_bh_update
One step for the UniP (B(h) version). Alternatively, `self.solver_p` is used if is specified. Args: model_output (`torch
dreamidv_wan_faster/utils/fm_solvers_unipc.py:350
↓ 1 callersMethodmultistep_uni_p_bh_update
One step for the UniP (B(h) version). Alternatively, `self.solver_p` is used if is specified. Args: model_output (`torch
dreamidv_wan/utils/fm_solvers_unipc.py:350
↓ 1 callersFunctionnms
Single class NMS implemented in Numpy.
pose/dwpose/onnxdet.py:8
↓ 1 callersFunctionpad_freqs
(original_tensor, target_len)
dreamidv_wan_faster/distributed/xdit_context_parallel.py:19
↓ 1 callersFunctionpad_freqs
(original_tensor, target_len)
dreamidv_wan/distributed/xdit_context_parallel.py:19
↓ 1 callersFunctionpad_tensor
(x, dim: int, padding_size: int)
dreamidv_wan_faster/distributed/xdit_context_parallel.py:12
↓ 1 callersFunctionpos_interpolate
(pos, seq_len)
dreamidv_wan_faster/modules/clip.py:22
↓ 1 callersFunctionpos_interpolate
(pos, seq_len)
dreamidv_wan/modules/clip.py:22
↓ 1 callersFunctionpostprocess
Postprocess for RTMPose model output. Args: outputs (np.ndarray): Output of RTMPose model. model_input_size (tuple): RTMPose mode
pose/dwpose/onnxpose.py:82
↓ 1 callersFunctionpreprocess
(img, input_size, swap=(2, 0, 1))
pose/dwpose/onnxdet.py:82
↓ 1 callersFunctionpreprocess
Do preprocessing for RTMPose model inference. Args: img (np.ndarray): Input image in shape. input_size (tuple): Input image size
pose/dwpose/onnxpose.py:9
↓ 1 callersMethodprocess
(self, input_data, ori_shape)
pose/extract.py:178
↓ 1 callersFunctionrand_name
(length=8, suffix='')
dreamidv_wan_faster/utils/utils.py:14
↓ 1 callersFunctionrand_name
(length=8, suffix='')
dreamidv_wan/utils/utils.py:14
↓ 1 callersFunctionread_video_frames
(video_path, use_type='cv2', is_rgb=True, info=False)
pose/extract.py:34
↓ 1 callersMethodreparameterize
(self, mu, log_var)
dreamidv_wan_faster/modules/vae.py:570
↓ 1 callersMethodreparameterize
(self, mu, log_var)
dreamidv_wan/modules/vae.py:570
↓ 1 callersFunctionresize_image
(input_image, resolution)
pose/dwpose/wholebody.py:28
↓ 1 callersMethodset_timesteps
Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):
dreamidv_wan_faster/utils/fm_solvers_unipc.py:160
↓ 1 callersMethodset_timesteps
Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):
dreamidv_wan/utils/fm_solvers_unipc.py:160
↓ 1 callersFunctionsmooth_pose_seq
(pose_seq, window_size=5)
express_adaption/media_pipe/__init__.py:68
↓ 1 callersMethodtime_shift
(self, mu: float, sigma: float, t: torch.Tensor)
dreamidv_wan_faster/utils/fm_solvers.py:337
↓ 1 callersMethodtime_shift
(self, mu: float, sigma: float, t: torch.Tensor)
dreamidv_wan_faster/utils/fm_solvers_unipc.py:276
↓ 1 callersMethodtime_shift
(self, mu: float, sigma: float, t: torch.Tensor)
dreamidv_wan/utils/fm_solvers.py:337
↓ 1 callersMethodtime_shift
(self, mu: float, sigma: float, t: torch.Tensor)
dreamidv_wan/utils/fm_solvers_unipc.py:276
↓ 1 callersFunctiontop_down_affine
Get the bbox image as the model input by affine transform. Args: input_size (dict): The input size of the model. bbox_scale (dict
pose/dwpose/onnxpose.py:257
↓ 1 callersFunctionumt5_xxl
(**kwargs)
dreamidv_wan_faster/modules/t5.py:456
↓ 1 callersFunctionumt5_xxl
(**kwargs)
dreamidv_wan/modules/t5.py:456
↓ 1 callersFunctionunflatten
( hid: torch.FloatTensor, # (L c) or (L ... c) hid_shape: torch.LongTensor, # (b n) )
dreamidv_wan/modules/projector.py:37
↓ 1 callersMethodvisual
(self, videos)
dreamidv_wan_faster/modules/clip.py:527
↓ 1 callersMethodvisual
(self, videos)
dreamidv_wan/modules/clip.py:527
↓ 1 callersFunctionzero_module
(module)
express_adaption/utils.py:29
Method__call__
(self, sequence, **kwargs)
dreamidv_wan_faster/modules/tokenizers.py:49
Method__call__
(self, texts, device)
dreamidv_wan_faster/modules/t5.py:506
Method__call__
(self, prompt, tar_lang="ch", image=None,
dreamidv_wan_faster/utils/prompt_extend.py:138
Method__call__
(self, x)
dreamidv_wan_faster/utils/na_resize.py:17
Method__call__
(self, image: Union[torch.Tensor, Image.Image])
dreamidv_wan_faster/utils/na_resize.py:27
Method__call__
(self, image: Union[torch.Tensor, Image.Image, List[Image.Image]])
dreamidv_wan_faster/utils/na_resize.py:53
Method__call__
(self, sequence, **kwargs)
dreamidv_wan/modules/tokenizers.py:49
Method__call__
(self, texts, device)
dreamidv_wan/modules/t5.py:506
Method__call__
(self, prompt, tar_lang="ch", image=None,
dreamidv_wan/utils/prompt_extend.py:138
Method__call__
(self, x)
dreamidv_wan/utils/na_resize.py:30
Method__call__
(self, image: Union[torch.Tensor, Image.Image])
dreamidv_wan/utils/na_resize.py:40
Method__call__
(self, image: Union[torch.Tensor, Image.Image, List[Image.Image]])
dreamidv_wan/utils/na_resize.py:66
Method__call__
(self, img)
express_adaption/media_pipe/mp_utils.py:51
Method__call__
(self, image: np.array)
express_adaption/media_pipe/__init__.py:31
Method__call__
(self, ref_result, temp_results)
express_adaption/media_pipe/__init__.py:135
Method__call__
(self, driving_seq_results, ref_face_result)
express_adaption/media_pipe/__init__.py:221
Method__call__
(self, ori_img)
pose/dwpose/wholebody.py:51
Method__init__
r""" Initializes the Wan text-to-video generation model components. Args: config (EasyDict): Object conta
dreamidv_wan_faster/wan_swapface.py:45
Method__init__
(self, name, seq_len=None, clean=None, **kwargs)
dreamidv_wan_faster/modules/tokenizers.py:39
Method__init__
(self, dim, num_heads, causal=False, attn_
dreamidv_wan_faster/modules/clip.py:55
Method__init__
(self, dim, mlp_ratio, num_heads, post_nor
dreamidv_wan_faster/modules/clip.py:114
Method__init__
(self, dim, mlp_ratio, num_heads, activati
dreamidv_wan_faster/modules/clip.py:158
Method__init__
(self, image_size=224, patch_size=16, dim=768,
dreamidv_wan_faster/modules/clip.py:211
Method__init__
(self, **kwargs)
dreamidv_wan_faster/modules/clip.py:305
Method__init__
(self, embed_dim=1024, image_size=224, patch_size=14,
dreamidv_wan_faster/modules/clip.py:330
Method__init__
(self, dtype, device, checkpoint_path, tokenizer_path)
dreamidv_wan_faster/modules/clip.py:503
Method__init__
(self, dim, eps=1e-6)
dreamidv_wan_faster/modules/t5.py:55
Method__init__
(self, dim, dim_attn, num_heads, dropout=0.1)
dreamidv_wan_faster/modules/t5.py:71
Method__init__
(self, dim, dim_ffn, dropout=0.1)
dreamidv_wan_faster/modules/t5.py:125
Method__init__
(self, dim, dim_attn, dim_ffn, num_heads,
dreamidv_wan_faster/modules/t5.py:146
Method__init__
(self, dim, dim_attn, dim_ffn, num_heads,
dreamidv_wan_faster/modules/t5.py:180
Method__init__
(self, num_buckets, num_heads, bidirectional, max_dist=128)
dreamidv_wan_faster/modules/t5.py:223
Method__init__
(self, vocab, dim, dim_attn, dim_ffn,
dreamidv_wan_faster/modules/t5.py:269
Method__init__
(self, vocab, dim, dim_attn, dim_ffn,
dreamidv_wan_faster/modules/t5.py:317
Method__init__
( self, text_len, dtype=torch.bfloat16, device=torch.cuda.current_device(),
dreamidv_wan_faster/modules/t5.py:474
Method__init__
(self, *args, **kwargs)
dreamidv_wan_faster/modules/vae.py:22
Method__init__
(self, dim, channel_first=True, images=True, bias=False)
dreamidv_wan_faster/modules/vae.py:41
Method__init__
(self, dim, mode)
dreamidv_wan_faster/modules/vae.py:68
Method__init__
(self, in_dim, out_dim, dropout=0.0)
dreamidv_wan_faster/modules/vae.py:188
Method__init__
(self, dim)
dreamidv_wan_faster/modules/vae.py:228
Method__init__
(self, dim=128, z_dim=4, dim_mult=[1, 2, 4, 4],
dreamidv_wan_faster/modules/vae.py:267
Method__init__
(self, dim=128, z_dim=4, dim_mult=[1, 2, 4, 4],
dreamidv_wan_faster/modules/vae.py:371
Method__init__
(self, dim=128, z_dim=4, dim_mult=[1, 2, 4, 4],
dreamidv_wan_faster/modules/vae.py:485
Method__init__
(self, cin=14, cout=16, vid_dim=1536, patch_size = [1,2,2] )
dreamidv_wan_faster/modules/projector.py:12
Method__init__
(self, dim, num_heads, dropout=0.1, eps=1e-5)
dreamidv_wan_faster/modules/xlm_roberta.py:12
Method__init__
(self, dim, num_heads, post_norm, dropout=0.1, eps=1e-5)
dreamidv_wan_faster/modules/xlm_roberta.py:51
Method__init__
(self, dim, eps=1e-5)
dreamidv_wan_faster/modules/model.py:73
Method__init__
(self, dim, eps=1e-6, elementwise_affine=False)
dreamidv_wan_faster/modules/model.py:92
Method__init__
(self, dim, num_heads, window_size=(-1, -1),
dreamidv_wan_faster/modules/model.py:105
Method__init__
(self, dim, num_heads, window_size=(-1, -1),
dreamidv_wan_faster/modules/model.py:187
Method__init__
(self, cross_attn_type, dim, ffn_dim, num_
dreamidv_wan_faster/modules/model.py:233
Method__init__
(self, in_dim, out_dim)
dreamidv_wan_faster/modules/model.py:345
Method__init__
r""" Initialize the diffusion model backbone. Args: model_type (`str`, *optional*, defaults to 't2v'): Mo
dreamidv_wan_faster/modules/model.py:369
Method__init__
Args: api_key: The API key for Dash Scope authentication and access to related services. model_name: Model name, 'qwe
dreamidv_wan_faster/utils/prompt_extend.py:159
Method__init__
Args: model_name: Use predefined model names such as 'QwenVL2.5_7B' and 'Qwen2.5_14B', which are specific version
dreamidv_wan_faster/utils/prompt_extend.py:309
Method__init__
(self, pattern: str, **kwargs)
dreamidv_wan_faster/utils/na_resize.py:13
Method__init__
(self, factor)
dreamidv_wan_faster/utils/na_resize.py:21
Method__init__
( self, max_area: float, downsample_only: bool = False, interpolation: Interpo
dreamidv_wan_faster/utils/na_resize.py:43
Method__init__
( self, num_train_timesteps: int = 1000, solver_order: int = 2, prediction_typ
dreamidv_wan_faster/utils/fm_solvers.py:129
Method__init__
( self, num_train_timesteps: int = 1000, solver_order: int = 2,
dreamidv_wan_faster/utils/fm_solvers_unipc.py:77
Method__init__
r""" Initializes the Wan text-to-video generation model components. Args: config (EasyDict): Object conta
dreamidv_wan/wan_swapface.py:45
Method__init__
(self, name, seq_len=None, clean=None, **kwargs)
dreamidv_wan/modules/tokenizers.py:39
Method__init__
(self, dim, num_heads, causal=False, attn_
dreamidv_wan/modules/clip.py:55
Method__init__
(self, dim, mlp_ratio, num_heads, post_nor
dreamidv_wan/modules/clip.py:114
Method__init__
(self, dim, mlp_ratio, num_heads, activati
dreamidv_wan/modules/clip.py:158
Method__init__
(self, image_size=224, patch_size=16, dim=768,
dreamidv_wan/modules/clip.py:211
Method__init__
(self, **kwargs)
dreamidv_wan/modules/clip.py:305
← previousnext →201–300 of 524, ranked by callers