Functions — github.com/Fannovel16/comfyui_controlnet

hub / github.com/Fannovel16/comfyui_controlnet_aux / functions

Functions4,192 in github.com/Fannovel16/comfyui_controlnet_aux

⨍ Functions 4,192◇ Types & classes 975↳ Endpoints 1

↓ 3 callersFunctionMatVecMult

(mtx, vec)

src/custom_manopth/smpl_handpca_wrapper_HAND_only.py:24

↓ 3 callersMethod__init__

(self)

src/custom_mmpkg/custom_mmcv/ops/points_sampler.py:165

↓ 3 callersMethod__init__

(self, *args, **kwargs)

src/custom_mmpkg/custom_mmcv/ops/deprecated_wrappers.py:11

↓ 3 callersMethod__init__

(self, in_channels, out_channels, **kwargs)

src/custom_mmpkg/custom_mmcv/ops/merge_cells.py:123

↓ 3 callersMethod__init__

(self, grad_clip=None)

src/custom_mmpkg/custom_mmcv/runner/hooks/optimizer.py:24

↓ 3 callersMethod__init__

(self, in_channels, sub_sample=False, conv_cfg=dict(type='C

src/custom_mmpkg/custom_mmcv/cnn/bricks/non_local.py:226

↓ 3 callersMethod__init__

(self, embed_dims=256, feedforward_channels=1024, num_fcs=2

src/custom_mmpkg/custom_mmcv/cnn/bricks/transformer.py:234

↓ 3 callersMethod__init__

(self, groups=1, base_width=4, radix=2, re

src/custom_mmpkg/custom_mmseg/models/backbones/resnest.py:291

↓ 3 callersMethod__init__

(self, in_channels=3, base_channels=64, num_stages=5,

src/custom_mmpkg/custom_mmseg/models/backbones/unet.py:277

↓ 3 callersMethod__init__

(self, in_channels=3, num_channels=(32, 64, 128), num_block

src/custom_mmpkg/custom_mmseg/models/backbones/cgnet.py:215

↓ 3 callersMethod__init__

(self, in_channels=3, downsample_dw_channels=(32, 48), glob

src/custom_mmpkg/custom_mmseg/models/backbones/fast_scnn.py:296

↓ 3 callersMethod__init__

(self, in_channels, out_channels)

src/custom_mesh_graphormer/modeling/_gcnn.py:115

↓ 3 callersMethod__init__

(self, inplanes, planes, stride=1, downsample=None)

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net_gridfeat.py:39

↓ 3 callersMethod__init__

(self, inplanes, planes, stride=1, downsample=None)

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net.py:39

↓ 3 callersMethod__init__

(self, input_dim=128, hidden_dim=256, out_dim=2, )

src/custom_controlnet_aux/unimatch/unimatch/reg_refine.py:7

↓ 3 callersMethod__init__

Args: dim (int): Number of input channels. num_heads (int): Number of attention heads in each ViT block.

src/custom_controlnet_aux/sam/modeling/image_encoder.py:122

↓ 3 callersMethod__init__

(self, dim: int, norm_layer: Callable[..., nn.Module] = nn.LayerNorm)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/swin_transformer.py:44

↓ 3 callersMethod__init__

(self, num_features, logdet=False, affine=True, allow_reverse_init=False)

src/custom_controlnet_aux/diffusion_edge/taming/modules/util.py:11

↓ 3 callersMethod__init__

(self, use_dropout=True)

src/custom_controlnet_aux/diffusion_edge/taming/modules/losses/lpips.py:14

↓ 3 callersFunction_auto_contrast_channel

(im, c, cutoff)

src/custom_mmpkg/custom_mmcv/image/photometric.py:257

↓ 3 callersMethod_ensure_lineidx_loaded

(self)

src/custom_mesh_graphormer/utils/tsv_file.py:93

↓ 3 callersMethod_init

(self, runner)

src/custom_mmpkg/custom_mmcv/runner/hooks/optimizer.py:84

↓ 3 callersFunction_load_checkpoint

Load checkpoint from somewhere (modelzoo, file, url). Args: filename (str): Accept local filepath, URL, ``torchvision://xxx``,

src/custom_mmpkg/custom_mmcv/runner/checkpoint.py:450

↓ 3 callersFunction_make_divisible

This function is taken from the original tf repo. It ensures that all layers have a channel number that is divisible by 8 It can be seen

src/custom_controlnet_aux/mlsd/models/mbv2_mlsd_large.py:72

↓ 3 callersMethod_make_layer

(self, in_channels, out_channels, blocks,

src/custom_mmpkg/custom_mmseg/models/backbones/fast_scnn.py:148

↓ 3 callersMethod_make_layer

(self, dim, stride=1, dilation=1, norm_layer=nn.InstanceNorm2d)

src/custom_controlnet_aux/unimatch/unimatch/backbone.py:92

↓ 3 callersMethod_make_stage

Make each stage.

src/custom_mmpkg/custom_mmseg/models/backbones/hrnet.py:454

↓ 3 callersMethod_make_stage

(self, layer_config, num_inchannels, multi_scale_output=True)

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net_gridfeat.py:415

↓ 3 callersMethod_make_stage

(self, layer_config, num_inchannels, multi_scale_output=True)

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net.py:415

↓ 3 callersMethod_make_transition_layer

Make transition layer.

src/custom_mmpkg/custom_mmseg/models/backbones/hrnet.py:371

↓ 3 callersMethod_make_transition_layer

( self, num_channels_pre_layer, num_channels_cur_layer)

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net_gridfeat.py:362

↓ 3 callersMethod_make_transition_layer

( self, num_channels_pre_layer, num_channels_cur_layer)

src/custom_mesh_graphormer/modeling/hrnet/hrnet_cls_net.py:362

↓ 3 callersMethod_pe_encoding

Positionally encode points that are normalized to [0,1].

src/custom_controlnet_aux/sam/modeling/prompt_encoder.py:185

↓ 3 callersMethod_register_module

(self, module_class, module_name=None, force=False)

src/custom_mmpkg/custom_mmcv/utils/registry.py:235

↓ 3 callersFunction_scale_channel

Scale the data in the corresponding channel.

src/custom_mmpkg/custom_mmcv/image/photometric.py:145

↓ 3 callersMethod_separate_heads

(self, x: Tensor, num_heads: int)

src/custom_controlnet_aux/sam/modeling/transformer.py:208

↓ 3 callersFunction_swin_transformer

( patch_size: List[int], embed_dim: int, depths: List[int], num_heads: List[int], window_s

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/swin_transformer.py:428

↓ 3 callersMethod_sync_params

(self)

src/custom_mmpkg/custom_mmcv/parallel/distributed_deprecated.py:37

↓ 3 callersFunctionabsolute_bbox

(relative_bbox: BoundingBox, width: int, height: int)

src/custom_controlnet_aux/diffusion_edge/taming/data/conditional_builder/utils.py:34

↓ 3 callersFunctionaccuracy

Calculate accuracy according to the prediction and target. Args: pred (torch.Tensor): The model prediction, shape (N, num_class, ...)

src/custom_mmpkg/custom_mmseg/models/losses/accuracy.py:4

↓ 3 callersFunctionallreduce_params

Allreduce parameters. Args: params (list[torch.Parameters]): List of parameters or buffers of a model. coalesce (bool

src/custom_mmpkg/custom_mmcv/runner/dist_utils.py:99

↓ 3 callersMethodapply_coords

Expects a numpy array of length 2 in the final dimension. Requires the original image size in (H, W) format.

src/custom_controlnet_aux/sam/utils/transforms.py:33

↓ 3 callersFunctionbatched_nms

Performs non-maximum suppression in a batched fashion. Modified from https://github.com/pytorch/vision/blob /505cd6957711af790211896d32b40291

src/custom_mmpkg/custom_mmcv/ops/nms.py:260

↓ 3 callersMethodbbox_from_token_pair

(self, token1: int, token2: int)

src/custom_controlnet_aux/diffusion_edge/taming/data/conditional_builder/objects_center_points.py:63

↓ 3 callersFunctioncalculate_stability_score

Computes the stability score for a batch of masks. The stability score is the IoU between the binary masks obtained by thresholding the p

src/custom_controlnet_aux/sam/utils/amg.py:156

↓ 3 callersFunctioncolor_val

Convert various input to color tuples. Args: color (:obj:`Color`/str/tuple/int/ndarray): Color inputs Returns: tuple[int]: A

src/custom_mmpkg/custom_mmcv/visualization/color.py:24

↓ 3 callersFunctioncompute_similarity_transform_batch

Batched version of compute_similarity_transform.

src/custom_mesh_graphormer/utils/metric_pampjpe.py:61

↓ 3 callersFunctionconv1x1

1x1 convolution

src/custom_controlnet_aux/leres/leres/Resnext_torch.py:25

↓ 3 callersFunctionconv1x1

1x1 convolution

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/resnet.py:54

↓ 3 callersFunctionconv3x3

3x3 convolution with padding

src/custom_controlnet_aux/leres/leres/Resnext_torch.py:19

↓ 3 callersFunctionconv3x3

3x3 convolution with padding

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/resnet.py:40

↓ 3 callersFunctionconvert_pil_to_tensor

(image: Image)

src/custom_controlnet_aux/diffusion_edge/taming/data/image_transforms.py:15

↓ 3 callersFunctionconvert_video

Convert a video with ffmpeg. This provides a general api to ffmpeg, the executed command is:: `ffmpeg -y <pre_options> -i <in_file> <opt

src/custom_mmpkg/custom_mmcv/video/processing.py:11

↓ 3 callersMethodcoordinates_from_token

(self, token: int)

src/custom_controlnet_aux/diffusion_edge/taming/data/conditional_builder/objects_center_points.py:58

↓ 3 callersFunctioncross_product

(u, v)

src/custom_manopth/rot6d.py:63

↓ 3 callersFunctioncustom_torch_download

Download PyTorch models using PyTorch 2.7's built-in download mechanism.

src/custom_controlnet_aux/util.py:265

↓ 3 callersFunctiondefault

(val, d)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/utils.py:27

↓ 3 callersMethoddetect

(self, image, max_faces=10, min_confidence=0.5, resolution=512)

node_wrappers/mediapipe_face.py:27

↓ 3 callersMethodencode_decode

Encode images with backbone and decode into a semantic segmentation map of the same size as input.

src/custom_mmpkg/custom_mmseg/models/segmentors/encoder_decoder.py:84

↓ 3 callersMethodevery_n_epochs

(self, runner, n)

src/custom_mmpkg/custom_mmcv/runner/hooks/hook.py:55

↓ 3 callersMethodforward

Return a list of heatmaps.

src/custom_controlnet_aux/dwpose/face.py:191

↓ 3 callersMethodforward_train

Placeholder for Forward function for training.

src/custom_mmpkg/custom_mmseg/models/segmentors/base.py:51

↓ 3 callersMethodforward_train

Forward function for training. Args: img (Tensor): Input images. img_metas (list[dict]): List of image info dict wher

src/custom_mmpkg/custom_mmseg/models/segmentors/encoder_decoder.py:136

↓ 3 callersFunctiongenerate_window_grid

(h_min, h_max, w_min, w_max, len_h, len_w, device=None)

src/custom_controlnet_aux/unimatch/unimatch/utils.py:6

↓ 3 callersFunctionget_class_weight

Get class weight for loss function. Args: class_weight (list[float] | str | None): If class_weight is a str, take it as a fil

src/custom_mmpkg/custom_mmseg/models/losses/utils.py:8

↓ 3 callersMethodget_dense_pe

Returns the positional encoding used to encode point prompts, applied to a dense set of points the shape of the image encoding.

src/custom_controlnet_aux/sam/modeling/prompt_encoder.py:62

↓ 3 callersMethodget_loss

(self, pred, target, mean=True)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ddm_const_sde.py:809

↓ 3 callersFunctionget_ort_providers

()

src/custom_controlnet_aux/dwpose/util.py:440

↓ 3 callersMethodget_text

Read data from a given ``filepath`` with 'r' mode. Args: filepath (str or Path): Path to read data. encoding (str): T

src/custom_mmpkg/custom_mmcv/fileio/file_client.py:994

↓ 3 callersMethodget_tsv_file

(self, tsv_file)

src/custom_mesh_graphormer/datasets/human_mesh_tsv.py:55

↓ 3 callersMethodget_tsv_file

(self, tsv_file)

src/custom_mesh_graphormer/datasets/hand_mesh_tsv.py:55

↓ 3 callersMethodhigh_quality_resize

(self, x, size)

hint_image_enchance.py:132

↓ 3 callersFunctionimpatch

(image, rect)

src/custom_controlnet_aux/leres/leres/depthmap.py:270

↓ 3 callersFunctionimresize

Resize image to a given size. Args: img (ndarray): The input image. size (tuple[int]): Target size (w, h). return_scale (

src/custom_mmpkg/custom_mmcv/image/geometric.py:51

↓ 3 callersFunctionimshow

Show an image. Args: img (str or ndarray): The image to be displayed. win_name (str): The window name. wait_time (int): V

src/custom_mmpkg/custom_mmcv/visualization/image.py:9

↓ 3 callersFunctionimwrite

Write image to file. Args: img (ndarray): Image array to be written. file_path (str): Image file path. params (None or li

src/custom_mmpkg/custom_mmcv/image/io.py:242

↓ 3 callersMethodinference

Inference with slide/whole style. Args: img (Tensor): The input image of shape (N, 3, H, W). img_meta (dict): Image i

src/custom_mmpkg/custom_mmseg/models/segmentors/encoder_decoder.py:233

↓ 3 callersFunctionis_normalized

(keypoints: List[Optional[Keypoint]])

src/custom_controlnet_aux/dwpose/util.py:71

↓ 3 callersFunctionload_from_http

load checkpoint through HTTP or HTTPS scheme path. In distributed setting, this function only download checkpoint at local rank 0. Args:

src/custom_mmpkg/custom_mmcv/runner/checkpoint.py:267

↓ 3 callersFunctionload_linelist_file

(linelist_file)

src/custom_mesh_graphormer/utils/tsv_file_ops.py:30

↓ 3 callersFunctionlocal_correlation_with_flow

(feature0, feature1, flow, local_radius,

src/custom_controlnet_aux/unimatch/unimatch/matching.py:86

↓ 3 callersFunctionmain_process

()

src/custom_controlnet_aux/metric3d/mono/utils/comm.py:20

↓ 3 callersMethodmake_block_plugins

make plugins for block. Args: in_channels (int): Input channels of plugin. plugins (list[dict]): List of plugins cfg

src/custom_mmpkg/custom_mmseg/models/backbones/resnet.py:219

↓ 3 callersFunctionmake_data_loader

(args, yaml_file, is_distributed=True, is_train=True, start_iter=0, scale_factor=1)

src/custom_mesh_graphormer/datasets/build.py:76

↓ 3 callersFunctionmake_layers

(block, no_relu_layers)

src/custom_controlnet_aux/open_pose/model.py:7

↓ 3 callersFunctionmake_layers

(block, no_relu_layers)

src/custom_controlnet_aux/dwpose/model.py:7

↓ 3 callersFunctionmerge_splits

(splits, num_splits=2, channel_last=False, )

src/custom_controlnet_aux/unimatch/unimatch/utils.py:62

↓ 3 callersFunctionnormalize_coords

(coords, h, w)

src/custom_controlnet_aux/unimatch/unimatch/utils.py:17

↓ 3 callersFunctionpidinet

()

src/custom_controlnet_aux/pidi/model.py:664

↓ 3 callersFunctionpool2x

(x)

src/custom_controlnet_aux/metric3d/mono/model/decode_heads/RAFTDepthNormalDPTDecoder5.py:350

↓ 3 callersFunctionposemap

(s)

src/custom_manopth/posemapper.py:33

↓ 3 callersMethodput

(self, key, val)

src/custom_mmpkg/custom_mmcv/video/io.py:30

↓ 3 callersMethodq_sample

(self, x_start, noise, t, C)

src/custom_controlnet_aux/diffusion_edge/denoising_diffusion_pytorch/ddm_const_sde.py:338

↓ 3 callersMethodreset

(self)

src/custom_controlnet_aux/metric3d/mono/utils/comm.py:184

↓ 3 callersMethodreset_image

Resets the currently set image.

src/custom_controlnet_aux/sam/predictor.py:262

↓ 3 callersFunctionsafe_numpy

(x)

utils.py:195

↓ 3 callersFunctionsafe_step

(x, step=2)

src/custom_controlnet_aux/util.py:119

↓ 3 callersFunctionsample_points

(init_normal, gt_norm_mask, sampling_ratio, beta)

src/custom_controlnet_aux/normalbae/nets/submodules/submodules.py:75

↓ 3 callersFunctionsave_checkpoint

(model, args, epoch, iteration, num_trial=10)

src/custom_mesh_graphormer/tools/run_gphmer_handmesh.py:46

↓ 3 callersFunctionscatter

Scatters tensor across multiple GPUs.

src/custom_mmpkg/custom_mmcv/parallel/_functions.py:6

← previous next →301–400 of 4,192, ranked by callers