MCPcopy Create free account

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

Functions491 in github.com/ali-vilab/VACE

⨍ Functions 491◇ Types & classes 128
↓ 1 callersFunction_make_pretrained_vitb16_384
(pretrained, use_readout='ignore', hooks=None)
vace/annotators/midas/vit.py:321
↓ 1 callersFunction_make_pretrained_vitb_rn50_384
(pretrained, use_readout='ignore', hooks
vace/annotators/midas/vit.py:496
↓ 1 callersFunction_make_pretrained_vitl16_384
(pretrained, use_readout='ignore', hooks=None)
vace/annotators/midas/vit.py:308
↓ 1 callersFunction_make_resnet_backbone
(resnet)
vace/annotators/midas/blocks.py:130
↓ 1 callersFunction_make_scratch
(in_shape, out_shape, groups=1, expand=False)
vace/annotators/depth_anything_v2/util/blocks.py:4
↓ 1 callersFunction_make_vit_b_rn50_backbone
( model, features=[256, 512, 768, 768], size=[384, 384], hooks=[0, 1, 8, 11], vit_features
vace/annotators/midas/vit.py:358
↓ 1 callersMethod_pillow_convert
(self, image, cvt_type='RGB')
vace/models/utils/preprocessor.py:15
↓ 1 callersMethod_resize_crop
Resize, center crop, convert to tensor, and normalize.
vace/models/utils/preprocessor.py:36
↓ 1 callersFunction_rotate_point
Rotate a point by an angle. Args: pt (np.ndarray): 2D point coordinates (x, y) in shape (2, ) angle_rad (float): rotation angle i
vace/annotators/dwpose/onnxpose.py:169
↓ 1 callersMethod_video_preprocess
(self, video, oh, ow)
vace/models/utils/preprocessor.py:147
↓ 1 callersMethodadd
(self, item)
vace/gradios/vace_ltx_demo.py:21
↓ 1 callersFunctionadd_residual
(x, brange, residual, residual_scale_factor, scaling_vector=None)
vace/annotators/depth_anything_v2/layers/block.py:142
↓ 1 callersFunctionalign_frames
(first_frame, last_frame)
vace/annotators/utils.py:291
↓ 1 callersFunctionbbox_xyxy2cs
Transform the bbox format from (x,y,w,h) into (center, scale) Args: bbox (ndarray): Bounding box(es) in shape (4,) or (n, 4), formatted
vace/annotators/dwpose/onnxpose.py:117
↓ 1 callersFunctionconvert_to_torch
(image)
vace/annotators/utils.py:65
↓ 1 callersMethodcreate_ui
(self, *args, **kwargs)
vace/gradios/vace_preprocess_demo.py:1046
↓ 1 callersMethodcreate_ui
(self, *args, **kwargs)
vace/gradios/vace_wan_demo.py:60
↓ 1 callersMethodcreate_ui
(self, *args, **kwargs)
vace/gradios/vace_ltx_demo.py:45
↓ 1 callersMethodcreate_ui_composition
(self, *args, **kwargs)
vace/gradios/vace_preprocess_demo.py:669
↓ 1 callersMethodcreate_ui_image
(self, *args, **kwargs)
vace/gradios/vace_preprocess_demo.py:78
↓ 1 callersMethodcreate_ui_video
(self, *args, **kwargs)
vace/gradios/vace_preprocess_demo.py:362
↓ 1 callersMethodcreate_ui_video_tool
(self, *args, **kwargs)
vace/gradios/vace_preprocess_demo.py:814
↓ 1 callersFunctiondecode
Modulate simcc distribution with Gaussian. Args: simcc_x (np.ndarray[K, Wx]): model predicted simcc in x. simcc_y (np.ndarray[K,
vace/annotators/dwpose/onnxpose.py:335
↓ 1 callersFunctiondemo_postprocess
(outputs, img_size, p6=False)
vace/annotators/dwpose/onnxdet.py:60
↓ 1 callersMethoddraw_contours
(self, canvas, contour, color)
vace/annotators/layout.py:74
↓ 1 callersMethoddraw_contours
(self, canvas, contour, color)
vace/annotators/layout.py:131
↓ 1 callersFunctiondrop_path
(x, drop_prob: float = 0.0, training: bool = False)
vace/annotators/depth_anything_v2/layers/drop_path.py:14
↓ 1 callersMethoddynamic_load
(self)
vace/models/wan/wan_vace.py:471
↓ 1 callersMethodfind_contours
(self, mask)
vace/annotators/layout.py:70
↓ 1 callersMethodfind_contours
(self, mask)
vace/annotators/layout.py:127
↓ 1 callersMethodforward
(self, frames)
vace/annotators/depth.py:44
↓ 1 callersMethodforward
(self, frames)
vace/annotators/flow.py:34
↓ 1 callersMethodforward
(self, frames)
vace/annotators/flow.py:51
↓ 1 callersMethodforward
(self, frames, ref_cfg=None, ref_num=None, return_mask=None, return_dict=None)
vace/annotators/frameref.py:23
↓ 1 callersMethodforward
(self, image=None, image_2=None, frames=None, frames_2=None, mode=None, expand_num=None, return_mask=None, ret
vace/annotators/frameref.py:81
↓ 1 callersMethodforward
(self, x)
vace/annotators/scribble.py:29
↓ 1 callersMethodforward
(self, frames)
vace/annotators/scribble.py:133
↓ 1 callersMethodforward
(self, image, return_image=None)
vace/annotators/salient.py:329
↓ 1 callersMethodforward
(self, frames, return_image=None)
vace/annotators/salient.py:357
↓ 1 callersMethodforward
(self, frames)
vace/annotators/pose.py:131
↓ 1 callersMethodforward
(self, frames)
vace/annotators/gray.py:19
↓ 1 callersMethodforward
(self, image, expand_ratio=0.3, direction=['left', 'right', 'u
vace/annotators/outpainting.py:127
↓ 1 callersMethodforward
(self, frames, expand_ratio=0.3, mask=None,
vace/annotators/outpainting.py:212
↓ 1 callersMethodforward
(self, frames, expand_ratio=0.3, direction=['left', 'right', 'up',
vace/annotators/outpainting.py:246
↓ 1 callersMethodforward
(self, image)
vace/annotators/gdino.py:83
↓ 1 callersMethodforward
(self, image)
vace/annotators/ram.py:35
↓ 1 callersMethodforward
(self, video, input_box=None, mask=None, task_
vace/annotators/sam2.py:119
↓ 1 callersMethodforward
(self, video, image=None)
vace/annotators/sam2.py:214
↓ 1 callersMethodforward
(self, video, image=None, classes=None, caption=None)
vace/annotators/sam2.py:231
↓ 1 callersMethodforward
(self, x)
vace/annotators/depth_anything_v2/dpt.py:38
↓ 1 callersMethodforward
(self, x: Tensor)
vace/annotators/depth_anything_v2/layers/block.py:82
↓ 1 callersMethodforward
(self, x: Tensor)
vace/annotators/depth_anything_v2/layers/attention.py:47
↓ 1 callersMethodforward
(self, x)
vace/annotators/midas/dpt_depth.py:62
↓ 1 callersMethodforward
(self, *args, **kwargs)
vace/models/ltx/models/transformers/attention.py:17
↓ 1 callersMethodforward_features
(self, x, masks=None)
vace/annotators/depth_anything_v2/dinov2.py:252
↓ 1 callersMethodforward_features_list
(self, x_list, masks_list)
vace/annotators/depth_anything_v2/dinov2.py:232
↓ 1 callersMethodforward_nested
x_list contains a list of tensors to nest together and run
vace/annotators/depth_anything_v2/layers/block.py:205
↓ 1 callersFunctionforward_vit
(pretrained, x)
vace/annotators/midas/vit.py:60
↓ 1 callersMethodgenerate
r""" Generates video frames from text prompt using diffusion process. Args: input_prompt (`str`): Text pr
vace/models/wan/wan_vace.py:262
↓ 1 callersMethodgenerate
(self, src_video=None, src_mask=None, src_ref_images=[], prompt="", negative_prompt="", seed=42,
vace/models/ltx/ltx_vace.py:79
↓ 1 callersFunctionget_branges_scales
(x, sample_drop_ratio=0.0)
vace/annotators/depth_anything_v2/layers/block.py:134
↓ 1 callersMethodget_intermediate_layers
( self, x: torch.Tensor, n: Union[int, Sequence] = 1, # Layers or n last
vace/annotators/depth_anything_v2/dinov2.py:296
↓ 1 callersMethodget_mask_func
(self, mask_cfg)
vace/annotators/maskaug.py:86
↓ 1 callersMethodget_mask_info
(self, mask)
vace/annotators/maskaug.py:49
↓ 1 callersFunctionget_parser
()
vace/vace_ltx_inference.py:32
↓ 1 callersFunctionget_parser
()
vace/vace_preproccess.py:30
↓ 1 callersFunctionget_parser
()
vace/vace_wan_inference.py:64
↓ 1 callersFunctionget_simcc_maximum
Get maximum response location and value from simcc representations. Note: instance number: N num_keypoints: K heatmap hei
vace/annotators/dwpose/onnxpose.py:290
↓ 1 callersMethodget_size
(self, width, height)
vace/annotators/depth_anything_v2/util/transform.py:62
↓ 1 callersMethodget_size
(self, width, height)
vace/annotators/midas/transforms.py:110
↓ 1 callersFunctionget_total_gpu_memory
()
vace/vace_ltx_inference.py:18
↓ 1 callersFunctionget_warp_matrix
Calculate the affine transformation matrix that can warp the bbox area in the input image to the output size. Args: center (np.ndarra
vace/annotators/dwpose/onnxpose.py:203
↓ 1 callersMethodimage2tensor
(self, raw_image, input_size=518)
vace/annotators/depth_anything_v2/dpt.py:58
↓ 1 callersMethodinfer_image
(self, raw_image, input_size=518)
vace/annotators/depth_anything_v2/dpt.py:50
↓ 1 callersFunctioninference
Inference RTMPose model. Args: sess (ort.InferenceSession): ONNXRuntime session. img (np.ndarray): Input image in shape. Ret
vace/annotators/dwpose/onnxpose.py:54
↓ 1 callersFunctioninference_detector
(session, oriImg)
vace/annotators/dwpose/onnxdet.py:100
↓ 1 callersFunctioninference_pose
(session, out_bbox, oriImg)
vace/annotators/dwpose/onnxpose.py:355
↓ 1 callersMethodinit_weights
(self)
vace/annotators/depth_anything_v2/dinov2.py:171
↓ 1 callersMethodinterpolate_pos_encoding
(self, x, w, h)
vace/annotators/depth_anything_v2/dinov2.py:178
↓ 1 callersMethodload_image
(self, data_key, **kwargs)
vace/models/utils/preprocessor.py:64
↓ 1 callersFunctionload_model
(model_type, model_path)
vace/annotators/midas/api.py:79
↓ 1 callersMethodload_video
(self, data_key, crop_box=None, seed=2024, **kwargs)
vace/models/utils/preprocessor.py:221
↓ 1 callersMethodload_video_pair
(self, data_key, data_key2, crop_box=None, seed=2024, **kwargs)
vace/models/utils/preprocessor.py:224
↓ 1 callersFunctionmain
()
vace/vace_pipeline.py:19
↓ 1 callersFunctionmain
(args)
vace/vace_ltx_inference.py:195
↓ 1 callersFunctionmain
(args)
vace/vace_preproccess.py:125
↓ 1 callersFunctionmain
(args)
vace/vace_wan_inference.py:196
↓ 1 callersFunctionmulticlass_nms
Multiclass NMS implemented in Numpy. Class-aware version.
vace/annotators/dwpose/onnxdet.py:37
↓ 1 callersFunctionnamed_apply
(fn: Callable, module: nn.Module, name="", depth_first=True, include_root=False)
vace/annotators/depth_anything_v2/dinov2.py:25
↓ 1 callersFunctionnms
Single class NMS implemented in Numpy.
vace/annotators/dwpose/onnxdet.py:8
↓ 1 callersFunctionpad_freqs
(original_tensor, target_len)
vace/models/wan/distributed/xdit_context_parallel.py:13
↓ 1 callersFunctionpostprocess
Postprocess for RTMPose model output. Args: outputs (np.ndarray): Output of RTMPose model. model_input_size (tuple): RTMPose mode
vace/annotators/dwpose/onnxpose.py:82
↓ 1 callersFunctionprepare_source
(src_video, src_mask, src_ref_images, num_frames, image_size, device)
vace/models/utils/preprocessor.py:251
↓ 1 callersFunctionpreprocess
(img, input_size, swap=(2, 0, 1))
vace/annotators/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
vace/annotators/dwpose/onnxpose.py:9
↓ 1 callersMethodprocess
(self, ori_img, ori_shape)
vace/annotators/pose.py:53
↓ 1 callersFunctionqkv_fn
(x)
vace/models/wan/distributed/xdit_context_parallel.py:197
↓ 1 callersFunctionread_mask
(mask_path, use_type='cv2', info=False)
vace/annotators/utils.py:157
↓ 1 callersMethodresize_crop
Resize, center crop and normalize for decord loaded video (torch.Tensor type) Parameters: video - video to process (torch.
vace/models/utils/preprocessor.py:108
↓ 1 callersFunctionresize_image_ori
(h, w, image, k)
vace/annotators/utils.py:91
← previousnext →101–200 of 491, ranked by callers