MCPcopy Create free account

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

Functions524 in github.com/bytedance/DreamID-V

⨍ Functions 524◇ Types & classes 122
↓ 21 callersFunctionl
(o)
assets/bootstrap.min.js:6
↓ 11 callersFunctions
(t,e,n)
assets/bootstrap.min.js:6
↓ 10 callersMethod_sigma_to_alpha_sigma_t
(self, sigma)
dreamidv_wan_faster/utils/fm_solvers.py:333
↓ 10 callersMethod_sigma_to_alpha_sigma_t
(self, sigma)
dreamidv_wan/utils/fm_solvers.py:333
↓ 8 callersMethod__init__
(self, vocab_size, dim, dim_attn, dim_ffn,
dreamidv_wan_faster/modules/t5.py:374
↓ 8 callersMethod__init__
(self, z_dim=16, vae_pth='cache/vae_step_411000.pth', dtype
dreamidv_wan_faster/modules/vae.py:621
↓ 8 callersMethod__init__
(self, vocab_size, dim, dim_attn, dim_ffn,
dreamidv_wan/modules/t5.py:374
↓ 8 callersMethod__init__
(self, z_dim=16, vae_pth='cache/vae_step_411000.pth', dtype
dreamidv_wan/modules/vae.py:621
↓ 8 callersMethod_sigma_to_alpha_sigma_t
(self, sigma)
dreamidv_wan_faster/utils/fm_solvers_unipc.py:272
↓ 8 callersMethod_sigma_to_alpha_sigma_t
(self, sigma)
dreamidv_wan/utils/fm_solvers_unipc.py:272
↓ 7 callersMethod__init__
(self, dim, out_dim, patch_size, eps=1e-6)
dreamidv_wan_faster/modules/model.py:315
↓ 7 callersMethod__init__
(self, dim, out_dim, patch_size, eps=1e-6)
dreamidv_wan/modules/model.py:332
↓ 7 callersFunctionflash_attention
q: [B, Lq, Nq, C1]. k: [B, Lk, Nk, C1]. v: [B, Lk, Nk, C2]. Nq must be divisible by Nk. q_lens
dreamidv_wan/modules/attention.py:24
↓ 6 callersMethod__init__
(self, dim, mid_dim)
dreamidv_wan_faster/modules/clip.py:96
↓ 6 callersMethod__init__
(self, dim, mid_dim)
dreamidv_wan/modules/clip.py:96
↓ 6 callersFunctione
(e,t)
assets/bootstrap.min.js:6
↓ 6 callersFunctionflash_attention
q: [B, Lq, Nq, C1]. k: [B, Lk, Nk, C1]. v: [B, Lk, Nk, C2]. Nq must be divisible by Nk. q_lens
dreamidv_wan_faster/modules/attention.py:24
↓ 6 callersMethodgenerate
r""" Generates video frames from text prompt using diffusion process. Args: input_prompt (`str`): Text pr
dreamidv_wan/wan_swapface.py:319
↓ 6 callersFunctionhalf
(x)
dreamidv_wan_faster/modules/attention.py:59
↓ 6 callersFunctionhalf
(x)
dreamidv_wan/modules/attention.py:59
↓ 6 callersFunctionhalf
(x)
dreamidv_wan/distributed/xdit_context_parallel.py:217
↓ 6 callersFunctioni
(t,e)
assets/bootstrap.min.js:6
↓ 5 callersFunctionfp16_clamp
(x)
dreamidv_wan_faster/modules/t5.py:20
↓ 5 callersFunctionfp16_clamp
(x)
dreamidv_wan/modules/t5.py:20
↓ 5 callersFunctiont
()
assets/bootstrap.min.js:6
↓ 4 callersFunctionNaResize
( resolution, # int or list downsample_only: bool, interpolation: InterpolationMode = Interpolatio
dreamidv_wan/utils/na_resize.py:107
↓ 4 callersFunctioncache_video
(tensor, save_file=None, fps=30, suffix='.mp4',
dreamidv_wan/utils/utils.py:23
↓ 4 callersFunctionceil_by_factor
Returns the smallest integer greater than or equal to 'number' that is divisible by 'factor'.
dreamidv_wan_faster/utils/qwen_vl_utils.py:44
↓ 4 callersFunctionceil_by_factor
Returns the smallest integer greater than or equal to 'number' that is divisible by 'factor'.
dreamidv_wan/utils/qwen_vl_utils.py:44
↓ 4 callersMethodclear_cache
(self)
dreamidv_wan_faster/modules/vae.py:582
↓ 4 callersMethodclear_cache
(self)
dreamidv_wan/modules/vae.py:582
↓ 4 callersMethodextend
(self, prompt, system_prompt, seed=-1, *args, **kwargs)
dreamidv_wan/utils/prompt_extend.py:128
↓ 4 callersFunctionn
(t)
assets/bootstrap.min.js:6
↓ 4 callersFunctionround_by_factor
Returns the closest integer to 'number' that is divisible by 'factor'.
dreamidv_wan_faster/utils/qwen_vl_utils.py:39
↓ 4 callersFunctionround_by_factor
Returns the closest integer to 'number' that is divisible by 'factor'.
dreamidv_wan/utils/qwen_vl_utils.py:39
↓ 4 callersFunctionsmart_resize
Rescales the image so that the following conditions are met: 1. Both dimensions (height and width) are divisible by 'factor'. 2. The to
dreamidv_wan_faster/utils/qwen_vl_utils.py:54
↓ 4 callersFunctionsmart_resize
Rescales the image so that the following conditions are met: 1. Both dimensions (height and width) are divisible by 'factor'. 2. The to
dreamidv_wan/utils/qwen_vl_utils.py:54
↓ 3 callersFunctionNaResize
( resolution, # int or list downsample_only: bool, interpolation: InterpolationMode = Interpolatio
dreamidv_wan_faster/utils/na_resize.py:94
↓ 3 callersMethod__len__
(self)
dreamidv_wan/utils/fm_solvers.py:856
↓ 3 callersFunctionbasic_clean
(text)
dreamidv_wan_faster/modules/tokenizers.py:12
↓ 3 callersFunctionbasic_clean
(text)
dreamidv_wan/modules/tokenizers.py:12
↓ 3 callersMethoddraw_landmarks
(self, image_size, keypoints, normed=False)
express_adaption/media_pipe/draw_util.py:146
↓ 3 callersMethodencode
videos: A list of videos each with shape [C, T, H, W].
dreamidv_wan_faster/modules/vae.py:647
↓ 3 callersMethodencode
videos: A list of videos each with shape [C, T, H, W].
dreamidv_wan/modules/vae.py:647
↓ 3 callersFunctionfloor_by_factor
Returns the largest integer less than or equal to 'number' that is divisible by 'factor'.
dreamidv_wan_faster/utils/qwen_vl_utils.py:49
↓ 3 callersFunctionfloor_by_factor
Returns the largest integer less than or equal to 'number' that is divisible by 'factor'.
dreamidv_wan/utils/qwen_vl_utils.py:49
↓ 3 callersFunctionget_video_npy
(video_path)
express_adaption/get_video_npy.py:39
↓ 3 callersFunctionhalf
(x)
dreamidv_wan_faster/distributed/xdit_context_parallel.py:188
↓ 3 callersFunctionprocess_dwpose
(input_video_path, output_pose_path, output_mask_path)
pose/extract.py:268
↓ 3 callersFunctionrope_apply
(x, grid_sizes, freqs)
dreamidv_wan/modules/model.py:41
↓ 3 callersFunctionrope_apply
x: [B, L, N, C]. grid_sizes: [B, 3]. freqs: [M, C // 2].
dreamidv_wan/distributed/xdit_context_parallel.py:33
↓ 3 callersFunctionrope_params
(max_seq_len, dim, theta=10000)
dreamidv_wan_faster/modules/model.py:30
↓ 3 callersFunctionrope_params
(max_seq_len, dim, theta=10000)
dreamidv_wan/modules/model.py:30
↓ 3 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.py:226
↓ 3 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.py:226
↓ 2 callersMethod__init__
(self, vocab_size=250002, max_seq_len=514, type_size=1,
dreamidv_wan_faster/modules/xlm_roberta.py:81
↓ 2 callersMethod__init__
(self, model_name, is_vl=False, device=0, **kwargs)
dreamidv_wan_faster/utils/prompt_extend.py:114
↓ 2 callersMethod__init__
(self, vocab_size=250002, max_seq_len=514, type_size=1,
dreamidv_wan/modules/xlm_roberta.py:81
↓ 2 callersMethod__init__
(self, model_name, is_vl=False, device=0, **kwargs)
dreamidv_wan/utils/prompt_extend.py:114
↓ 2 callersMethod__len__
(self)
dreamidv_wan_faster/utils/fm_solvers.py:856
↓ 2 callersFunction_get_3rd_point
To calculate the affine matrix, three pairs of points are required. This function is used to get the 3rd point, given 2D points a & b. The 3r
pose/dwpose/onnxpose.py:184
↓ 2 callersMethod_threshold_sample
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t
dreamidv_wan_faster/utils/fm_solvers.py:292
↓ 2 callersMethod_threshold_sample
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t
dreamidv_wan_faster/utils/fm_solvers_unipc.py:230
↓ 2 callersMethod_threshold_sample
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t
dreamidv_wan/utils/fm_solvers.py:292
↓ 2 callersMethod_threshold_sample
"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t
dreamidv_wan/utils/fm_solvers_unipc.py:230
↓ 2 callersFunctioncount_conv3d
(model)
dreamidv_wan_faster/modules/vae.py:475
↓ 2 callersFunctioncount_conv3d
(model)
dreamidv_wan/modules/vae.py:475
↓ 2 callersFunctioncreate_perspective_matrix
(aspect_ratio)
express_adaption/media_pipe/pose_util.py:18
↓ 2 callersMethoddecode
(self, zs)
dreamidv_wan_faster/modules/vae.py:657
↓ 2 callersMethoddecode
(self, zs)
dreamidv_wan/modules/vae.py:657
↓ 2 callersMethodencode
(self, x, scale)
dreamidv_wan_faster/modules/vae.py:516
↓ 2 callersMethodencode
(self, x, scale)
dreamidv_wan/modules/vae.py:516
↓ 2 callersFunctioneuler_and_translation_to_matrix
(euler_angles, translation_vector)
express_adaption/media_pipe/pose_util.py:73
↓ 2 callersMethodextend
(self, prompt, system_prompt, seed=-1, *args, **kwargs)
dreamidv_wan_faster/utils/prompt_extend.py:128
↓ 2 callersFunctionfetch_image
(ele: dict[str, str | Image.Image], size_factor: int = IMAGE_FACTOR)
dreamidv_wan_faster/utils/qwen_vl_utils.py:85
↓ 2 callersFunctionfetch_image
(ele: dict[str, str | Image.Image], size_factor: int = IMAGE_FACTOR)
dreamidv_wan/utils/qwen_vl_utils.py:85
↓ 2 callersFunctionflatten
( hid: List[torch.FloatTensor], # List of (*** c) )
dreamidv_wan/modules/projector.py:26
↓ 2 callersMethodforward
(self, x)
dreamidv_wan_faster/modules/clip.py:106
↓ 2 callersMethodforward
(self, x)
dreamidv_wan_faster/modules/vae.py:510
↓ 2 callersMethodforward
(self, x)
dreamidv_wan/modules/clip.py:106
↓ 2 callersMethodforward
(self, x)
dreamidv_wan/modules/vae.py:510
↓ 2 callersMethodgenerate
r""" Generates video frames from text prompt using diffusion process. Args: input_prompt (`str`): Text pr
dreamidv_wan_faster/wan_swapface.py:288
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
dreamidv_wan_faster/utils/fm_solvers.py:679
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
dreamidv_wan_faster/utils/fm_solvers_unipc.py:628
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
dreamidv_wan/utils/fm_solvers.py:679
↓ 2 callersMethodindex_for_timestep
(self, timestep, schedule_timesteps=None)
dreamidv_wan/utils/fm_solvers_unipc.py:628
↓ 2 callersFunctiono
(t)
assets/bootstrap.min.js:6
↓ 2 callersFunctionpad_tensor
(x, dim: int, padding_size: int)
dreamidv_wan/distributed/xdit_context_parallel.py:12
↓ 2 callersFunctionproject_points_with_trans
(points_3d, transformation_matrix, image_shape)
express_adaption/media_pipe/pose_util.py:57
↓ 2 callersFunctionqkv_fn
(x)
dreamidv_wan_faster/distributed/xdit_context_parallel.py:192
↓ 2 callersFunctionqkv_fn
(x)
dreamidv_wan/distributed/xdit_context_parallel.py:221
↓ 2 callersFunctionrope_apply
(x, grid_sizes, freqs)
dreamidv_wan_faster/modules/model.py:41
↓ 2 callersFunctionrope_apply
x: [B, L, N, C]. grid_sizes: [B, 3]. freqs: [M, C // 2].
dreamidv_wan_faster/distributed/xdit_context_parallel.py:33
↓ 2 callersFunctionsave_landmarks_as_video
Visualizes a sequence of 2D landmarks and saves them as a video. Args: landmarks_sequence (np.array): A NumPy array of shape (num_fra
express_adaption/media_pipe/__init__.py:79
↓ 2 callersFunctionsave_one_video
(file_path, videos, fps=30, quality=8)
pose/extract.py:70
↓ 2 callersFunctionsave_visualization_video
(landmarks_sequence, output_filename, frame_size, fps=30, mode='points')
generate_dreamidv.py:60
↓ 2 callersFunctionsave_visualization_video
(landmarks_sequence, output_filename, frame_size, fps=30, mode='points', optional_face_oval_indices=None)
express_adaption/align_refvideo.py:61
↓ 2 callersFunctionsinusoidal_embedding_1d
(dim, position)
dreamidv_wan_faster/modules/model.py:16
↓ 2 callersFunctionsinusoidal_embedding_1d
(dim, position)
dreamidv_wan/modules/model.py:16
↓ 2 callersFunctionsmart_nframes
calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the configuration of video.
dreamidv_wan_faster/utils/qwen_vl_utils.py:133
next →1–100 of 524, ranked by callers