MCPcopy Create free account

hub / github.com/ali-vilab/VACE / functions

Functions491 in github.com/ali-vilab/VACE

⨍ Functions 491◇ Types & classes 128
Methodforward
Forward pass. Args: x (tensor): input data (image) Returns: tensor: depth
vace/annotators/midas/midas_net.py:53
Methodforward
(self, x)
vace/annotators/midas/api.py:163
Methodforward
(self, x)
vace/annotators/midas/dpt_depth.py:106
Methodforward
(self, c, x, **kwargs)
vace/models/wan/modules/model.py:33
Methodforward
(self, x, hints, context_scale=1.0, **kwargs)
vace/models/wan/modules/model.py:63
Methodforward
The [`Transformer2DModel`] forward method. Args: hidden_states (`torch.LongTensor` of shape `(batch size, num latent pix
vace/models/ltx/models/transformers/transformer3d.py:249
Methodforward
(self, *args, **kwargs)
vace/models/ltx/models/transformers/attention.py:40
Functionforward_flex
(self, x)
vace/annotators/midas/vit.py:125
Functionfuse_model
(m)
vace/annotators/midas/midas_net_custom.py:145
Methodgenerate
(self, output_gallery, src_video, src_mask, src_ref_image_1, src_ref_image_2, src_ref_image_3, prompt, negativ
vace/gradios/vace_wan_demo.py:203
Methodgenerate
(self, output_gallery, src_video, src_mask, src_ref_image_1, src_ref_image_2, src_ref_image_3, prompt, negativ
vace/gradios/vace_ltx_demo.py:181
Methodgenerate
(self, input_prompt, input_frames, input_masks,
vace/models/wan/wan_vace.py:697
Methodgenerate_bbox_mask
(self, mask, bbox, h, w, expand_ratio=None, expand_iters=None, expand_lrtp=None)
vace/annotators/maskaug.py:175
Methodgenerate_hull_mask
(self, mask, bbox, h, w, clockwise=None, expand_ratio=None, expand_iters=None, expand_lrtp=None)
vace/annotators/maskaug.py:162
Methodgenerate_mask
(self, mask, bbox, h, w, expand_ratio=None, expand_iters=None, expand_lrtp=None)
vace/annotators/maskaug.py:118
FunctionhandDetect
(candidate, subset, oriImg)
vace/annotators/dwpose/util.py:157
Functionhook
(model, input, output)
vace/annotators/midas/vit.py:166
Functioninit_weights_vit_timm
ViT weight initialization, original timm impl (for reproducibility)
vace/annotators/depth_anything_v2/dinov2.py:330
Methodload_image_pair
(self, data_key, data_key2, **kwargs)
vace/models/utils/preprocessor.py:67
Functionload_midas_transform
(model_type)
vace/annotators/midas/api.py:32
Methodmp_worker
(self, gpu, gpu_infer, pmi_rank, pmi_world_size, in_q_list, out_q, initialized_events, work_env)
vace/models/wan/wan_vace.py:504
Methodnoop_no_sync
()
vace/models/wan/wan_vace.py:360
Methodnoop_no_sync
()
vace/models/wan/wan_vace.py:614
Functionnpmax
(array)
vace/annotators/dwpose/util.py:294
FunctionpadRightDownCorner
(img, stride, padValue)
vace/annotators/dwpose/util.py:40
Functionparse_bboxes
(s)
vace/vace_preproccess.py:16
Functionpostproccess
()
vace/vace_preproccess.py:122
Functionpreproccess
()
vace/vace_preproccess.py:116
Functionproccess
()
vace/vace_preproccess.py:119
Methodprocess_composition_data
(self, input_process_video_1, input_process_video_2, input_process_video_mask_1, input_process_video_mask_2, i
vace/gradios/vace_preprocess_demo.py:739
Methodprocess_image_data
(self, input_process_image, image_process_type, outpainting_direction, outpainting_ratio, mask_process_type,
vace/gradios/vace_preprocess_demo.py:227
Methodprocess_tool_data
(self, input_process_image_1, input_process_image_2, input_process_video_1, input_process_video_2, input_proce
vace/gradios/vace_preprocess_demo.py:924
Methodprocess_video_data
(self, input_process_video, input_process_image, video_process_type, outpainting_direction, outpainting_ratio,
vace/gradios/vace_preprocess_demo.py:513
Functionread_image
Read image and output RGB image (0-1). Args: path (str): path to file Returns: array: RGB image (0-1)
vace/annotators/midas/utils.py:101
Functionread_pfm
Read pfm file. Args: path (str): path to file Returns: tuple: (data, scale)
vace/annotators/midas/utils.py:12
Functionread_video_last_frame
(video_path, use_type='cv2', is_rgb=True)
vace/annotators/utils.py:256
Functionresize_depth
Resize depth map and bring to CPU (numpy). Args: depth (tensor): depth width (int): image width height (int): image heigh
vace/annotators/midas/utils.py:150
Functionresize_image
(input_image, resolution)
vace/annotators/dwpose/wholebody.py:28
Functionresize_image
Resize image and make it fit for network. Args: img (array): image Returns: tensor: data ready for network
vace/annotators/midas/utils.py:120
Methodsave_composition_data
(self, video_path, mask_path)
vace/gradios/vace_preprocess_demo.py:775
Methodsave_image_data
(self, input_image, image, masked_image, mask)
vace/gradios/vace_preprocess_demo.py:281
Methodsave_tool_data
(self, image_path, video_path, mask_path)
vace/gradios/vace_preprocess_demo.py:1002
Methodsave_video_data
(self, input_video_path, input_image, video_path, masked_video_path, mask_path)
vace/gradios/vace_preprocess_demo.py:582
MethodsetUp
(self)
tests/test_annotators.py:13
Functionsmart_resize
(x, s)
vace/annotators/dwpose/util.py:12
Functionsmart_resize_k
(x, fx, fy)
vace/annotators/dwpose/util.py:26
MethodtearDown
(self)
tests/test_annotators.py:25
Methodtest_annotator_depth_image
(self)
tests/test_annotators.py:108
Methodtest_annotator_depth_video
(self)
tests/test_annotators.py:120
Methodtest_annotator_depth_video_2
(self)
tests/test_annotators.py:135
Methodtest_annotator_flow_video
(self)
tests/test_annotators.py:186
Methodtest_annotator_frameref_video_1
(self)
tests/test_annotators.py:198
Methodtest_annotator_frameref_video_2
(self)
tests/test_annotators.py:216
Methodtest_annotator_gdino_v1
(self)
tests/test_annotators.py:409
Methodtest_annotator_gdino_v2
(self)
tests/test_annotators.py:421
Methodtest_annotator_gdino_with_ram
(self)
tests/test_annotators.py:433
Methodtest_annotator_gray_image
(self)
tests/test_annotators.py:29
Methodtest_annotator_gray_video
(self)
tests/test_annotators.py:39
Methodtest_annotator_gray_video_2
(self)
tests/test_annotators.py:52
Methodtest_annotator_layout_mask_video
(self)
tests/test_annotators.py:334
Methodtest_annotator_layout_mask_video_2
(self)
tests/test_annotators.py:355
Methodtest_annotator_layout_video
(self)
tests/test_annotators.py:322
Methodtest_annotator_maskaug_video
(self)
tests/test_annotators.py:378
Methodtest_annotator_outpainting_1
(self)
tests/test_annotators.py:230
Methodtest_annotator_outpainting_inner_1
(self)
tests/test_annotators.py:264
Methodtest_annotator_outpainting_inner_video_1
(self)
tests/test_annotators.py:281
Methodtest_annotator_outpainting_video_1
(self)
tests/test_annotators.py:247
Methodtest_annotator_pose_image
(self)
tests/test_annotators.py:63
Methodtest_annotator_pose_video
(self)
tests/test_annotators.py:77
Methodtest_annotator_pose_video_2
(self)
tests/test_annotators.py:94
Methodtest_annotator_prompt_extend
(self)
tests/test_annotators.py:529
Methodtest_annotator_prompt_extend_ds
(self)
tests/test_annotators.py:555
Methodtest_annotator_ram
(self)
tests/test_annotators.py:398
Methodtest_annotator_salient
(self)
tests/test_annotators.py:298
Methodtest_annotator_salient_video
(self)
tests/test_annotators.py:310
Methodtest_annotator_sam2
(self)
tests/test_annotators.py:452
Methodtest_annotator_sam2_image
(self)
tests/test_annotators.py:518
Methodtest_annotator_sam2gdinoram_video
(self)
tests/test_annotators.py:494
Methodtest_annotator_sam2salient
(self)
tests/test_annotators.py:470
Methodtest_annotator_scribble_image
(self)
tests/test_annotators.py:147
Methodtest_annotator_scribble_video
(self)
tests/test_annotators.py:159
Methodtest_annotator_scribble_video_2
(self)
tests/test_annotators.py:174
Functiontransfer
(model, model_weights)
vace/annotators/dwpose/util.py:63
Functionusp_attn_forward
(self, x, seq_lens, grid_sizes,
vace/models/wan/distributed/xdit_context_parallel.py:184
Functionusp_dit_forward
x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings each with s
vace/models/wan/distributed/xdit_context_parallel.py:97
Functionusp_dit_forward_vace
( self, x, vace_context, seq_len, kwargs )
vace/models/wan/distributed/xdit_context_parallel.py:67
Functionvit_base
(patch_size=16, num_register_tokens=0, **kwargs)
vace/annotators/depth_anything_v2/dinov2.py:352
Functionvit_giant2
Close to ViT-giant, with embed-dim 1536 and 24 heads => embed-dim per head 64
vace/annotators/depth_anything_v2/dinov2.py:380
Functionvit_large
(patch_size=16, num_register_tokens=0, **kwargs)
vace/annotators/depth_anything_v2/dinov2.py:366
Functionvit_small
(patch_size=16, num_register_tokens=0, **kwargs)
vace/annotators/depth_anything_v2/dinov2.py:338
Functionwrite_depth
Write depth map to pfm and png file. Args: path (str): filepath without extension depth (array): depth
vace/annotators/midas/utils.py:169
← previous401–491 of 491, ranked by callers