MCPcopy Create free account

hub / github.com/MyNiuuu/AniCrafter / functions

Functions5,947 in github.com/MyNiuuu/AniCrafter

⨍ Functions 5,947◇ Types & classes 1,261↳ Endpoints 36
↓ 1 callersFunctionSSIM
(x, y)
engine/BiRefNet/loss.py:223
↓ 1 callersMethod__init__
(self, model_path, device)
LHM/utils/face_detector.py:159
↓ 1 callersMethod__init__
( self, transformer_dim: int, transformer_layers: int, transformer_heads: int,
LHM/models/modeling_human_lrm.py:40
↓ 1 callersMethod__init__
(self, in_channels=3, cond_channels=0, hidden_channels=512, depth=6)
LHM/models/discriminator.py:19
↓ 1 callersMethod__init__
(self, opt, que, qid)
LHM/models/ESRGANer_utils.py:368
↓ 1 callersMethod__init__
( self, in_channels, inner_channels, use_clstoken=False, out_channel=1
LHM/models/encoders/dinov2_fusion_wrapper.py:28
↓ 1 callersMethod__init__
(self, model_name="swin_base_patch4_window12_384_in22k", encoder_feat_dim=384)
LHM/models/encoders/xunet_wrapper.py:24
↓ 1 callersMethod__init__
Init. Args: features (int): number of features
LHM/models/encoders/dpt_util/blocks.py:33
↓ 1 callersMethod__init__
( self, dim: int, num_heads: int, mlp_ratio: float = 4.0, qkv_bias: bo
LHM/models/encoders/dinov2/layers/block.py:50
↓ 1 callersMethod__init__
( self, in_features: int, hidden_features: Optional[int] = None, out_features:
LHM/models/encoders/dinov2/layers/swiglu_ffn.py:15
↓ 1 callersMethod__init__
SMPLX using pytorch3d subdivsion
LHM/models/rendering/smpl_x.py:55
↓ 1 callersMethod__init__
SMPLX using dense sampling
LHM/models/rendering/smpl_x_voxel_dense_sampling.py:59
↓ 1 callersMethod__init__
(self, norm_type='l2', gt_edges=None, gt_edge_path='', est_
LHM/models/rendering/smplx/transfer_model/losses/losses.py:73
↓ 1 callersMethod__init__
(self, module: torch.nn.Module, offload_dtype, offload_device, onload_dtype, onload_device, computation_dtype,
diffsynth/vram_management/layers.py:12
↓ 1 callersMethod__init__
(self, processor, model, scale=1.0)
diffsynth/controlnets/controlnet_unit.py:15
↓ 1 callersMethod__init__
(self, num_inference_steps, rel_l1_thresh)
diffsynth/pipelines/hunyuan_video.py:252
↓ 1 callersMethod__init__
(self, num_inference_steps, rel_l1_thresh)
diffsynth/pipelines/flux_image.py:473
↓ 1 callersMethod__init__
(self)
diffsynth/pipelines/hunyuan_image.py:16
↓ 1 callersMethod__init__
(self, num_tokens_for_img: int, offload_kv_cache: bool=False)
diffsynth/pipelines/omnigen_image.py:16
↓ 1 callersMethod__init__
(self)
diffsynth/prompters/omost.py:124
↓ 1 callersMethod__init__
(self, input_size: int, xcol: str = "emb", ycol: str = "avg_rating")
diffsynth/extensions/ImageQualityMetric/aesthetic.py:11
↓ 1 callersMethod__init__
( self, local_loss=False, gather_with_grad=False, cache_labels
diffsynth/extensions/ImageQualityMetric/open_clip/loss.py:69
↓ 1 callersMethod__init__
(self, max_size, interpolation=InterpolationMode.BICUBIC, fn='max', fill=0)
diffsynth/extensions/ImageQualityMetric/open_clip/transform.py:28
↓ 1 callersMethod__init__
(self, use_pooler_output=True)
diffsynth/extensions/ImageQualityMetric/open_clip/hf_model.py:68
↓ 1 callersMethod__init__
( self, embed_dim: int, vision_cfg: CLIPVisionCfg, text_cfg: C
diffsynth/extensions/ImageQualityMetric/open_clip/model.py:179
↓ 1 callersMethod__init__
(self, ckpt, config_file=False)
diffsynth/extensions/ImageQualityMetric/trainer/models/clip_model.py:99
↓ 1 callersMethod__init__
(self, global_pool=False)
diffsynth/models/sdxl_controlnet.py:44
↓ 1 callersMethod__init__
(self)
diffsynth/models/hunyuan_dit_text_encoder.py:89
↓ 1 callersMethod__init__
(self, upcast_to_float32=True)
diffsynth/models/sdxl_vae_encoder.py:5
↓ 1 callersMethod__init__
( self, torch_dtype=torch.float16, device="cuda", model_id_list: List[Preset_m
diffsynth/models/model_manager.py:318
↓ 1 callersMethod__init__
(self, config: LlamaConfig)
diffsynth/models/hunyuan_video_text_encoder.py:8
↓ 1 callersMethod__init__
(self)
diffsynth/models/svd_vae_encoder.py:5
↓ 1 callersMethod__init__
(self, embed_dim=768, vocab_size=49408, max_position_embeddings=77, num_encoder_layers=12, encoder_intermediat
diffsynth/models/sd_text_encoder.py:40
↓ 1 callersMethod__init__
(self, upcast_to_float32=True)
diffsynth/models/sdxl_vae_decoder.py:5
↓ 1 callersMethod__init__
(self, embed_dim=1280, layer_norm_eps=1e-5, num_encoder_layers=32, encoder_intermediate_size=5120, projection_
diffsynth/models/svd_image_encoder.py:28
↓ 1 callersMethod__init__
(self)
diffsynth/models/flux_vae.py:6
↓ 1 callersMethod__init__
(self)
diffsynth/models/sd_vae_decoder.py:45
↓ 1 callersMethod__init__
(self, embed_dim=768, vocab_size=49408, max_position_embeddings=77, num_encoder_layers=11, encoder_intermediat
diffsynth/models/sdxl_text_encoder.py:6
↓ 1 callersMethod__init__
(self)
diffsynth/models/sd_ipadapter.py:19
↓ 1 callersMethod__init__
(self, global_pool=False)
diffsynth/models/sd_controlnet.py:26
↓ 1 callersMethod__init__
(self, optimizer, milestones, gamma=0.1, r
ProPainter/core/lr_scheduler.py:20
↓ 1 callersMethod__init__
( self, cam_intrinsics, init_pose, j3d_idx, device, )
engine/pose_estimation/smplify.py:132
↓ 1 callersMethod__init__
( self, num_body_joints=52, context_dim=1280, dim=1024, depth=2,
engine/pose_estimation/model.py:559
↓ 1 callersMethod__init__
(self, model)
engine/pose_estimation/dinov2/dinov2/eval/utils.py:22
↓ 1 callersMethod__init__
(self, train_features, train_labels, nb_knn, T, device, num_classes=1000)
engine/pose_estimation/dinov2/dinov2/eval/knn.py:109
↓ 1 callersMethod__init__
( self, in_features: int, hidden_features: Optional[int] = None, out_features:
engine/pose_estimation/dinov2/dinov2/layers/swiglu_ffn.py:15
↓ 1 callersMethod__init__
(self, width, height, K, device, faces=None)
engine/pose_estimation/pose_utils/render.py:135
↓ 1 callersMethod__init__
(self, msg: str = '', data: Optional[Dict] = None)
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/utils/message.py:26
↓ 1 callersMethod__init__
(self, dataloader, start=None, interval=1,
engine/pose_estimation/third-party/ViTPose/mmpose/core/evaluation/eval_hooks.py:15
↓ 1 callersMethod__init__
(self, depth, groups=32, width_per_group=4, **kwargs)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/resnext.py:152
↓ 1 callersMethod__init__
(self, downsample_times=4, num_stacks=1, out_channels=34,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/hourglass_ae.py:102
↓ 1 callersMethod__init__
(self, in_channels, stem_channels=1024, num_blocks=2,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/tcn.py:179
↓ 1 callersMethod__init__
(self, extra, in_channels=3, conv_cfg=None,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/hrnet.py:275
↓ 1 callersMethod__init__
(self, depth, se_ratio=16, **kwargs)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/seresnet.py:118
↓ 1 callersMethod__init__
(self, widen_factor=1.0, out_indices=(3, ), frozen_stages=-
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/shufflenet_v2.py:158
↓ 1 callersMethod__init__
(self, in_channels, out_channels, groups=3,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/shufflenet_v1.py:47
↓ 1 callersMethod__init__
(self, depth, groups=32, width_per_group=4, **kwargs)
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/seresnext.py:158
↓ 1 callersMethod__init__
(self, in_channels, out_channels, feat_channels=128,
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/cpm.py:86
↓ 1 callersMethod__init__
(self, widen_factor=1., out_indices=(7, ), frozen_stages=-1
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/mobilenet_v2.py:130
↓ 1 callersMethod__init__
(self, downsample_times=5, num_stacks=2, stage_channels=(25
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/hourglass.py:120
↓ 1 callersMethod__init__
Get results from the 3D human pose heatmap. Instead of obtaining maximums on the heatmap, this module regresses the coordinates of key
engine/pose_estimation/third-party/ViTPose/mmpose/models/heads/voxelpose_head.py:130
↓ 1 callersMethod__init__
(self, gan_type, real_label_val=1.0, fake_label_val=0.0,
engine/pose_estimation/third-party/ViTPose/mmpose/models/losses/mesh_loss.py:263
↓ 1 callersMethod__init__
(self)
engine/BiRefNet/models/modules/utils.py:47
↓ 1 callersMethod__init__
(self, in_channels=64, out_channels=None, inter_channels=64)
engine/BiRefNet/models/modules/decoder_blocks.py:40
↓ 1 callersMethod__iter__
(self)
ProPainter/core/prefetch_dataloader.py:36
↓ 1 callersMethod__len__
(self)
LHM/datasets/base.py:25
↓ 1 callersMethod__len__
(self)
diffsynth/extensions/FastBlend/data.py:123
↓ 1 callersMethod__setattr__
(self, name: Any, value: Any)
LHM/outputs/base.py:91
↓ 1 callersMethod__setattr__
(self, name: Any, value: Any)
engine/ouputs.py:91
↓ 1 callersMethod__setitem__
(self, key, value)
LHM/outputs/base.py:97
↓ 1 callersMethod__setitem__
(self, key, value)
engine/ouputs.py:97
↓ 1 callersMethod_accumulate_paf_map_
Accumulate part affinity fields between two given joints. Args: pafs (np.ndarray[2,H,W]): paf maps (2 dimensions:x axis and
engine/pose_estimation/third-party/ViTPose/mmpose/datasets/pipelines/bottom_up_transform.py:289
↓ 1 callersFunction_allreduce_coalesced
Allreduce parameters as a whole.
engine/pose_estimation/third-party/ViTPose/mmpose/core/utils/dist_utils.py:9
↓ 1 callersFunction_axis_angle_rotation
Return the rotation matrices for one of the rotations about an axis of which Euler angles describe, for each value of the angle given. A
LHM/utils/rot6d.py:176
↓ 1 callersFunction_axis_angle_rotation
Return the rotation matrices for one of the rotations about an axis of which Euler angles describe, for each value of the angle given. A
engine/pose_estimation/pose_utils/rot6d.py:169
↓ 1 callersFunction_box2cs
(box, image_size)
engine/pose_estimation/third-party/ViTPose/tests/test_pipelines/test_top_down_pipelines.py:53
↓ 1 callersMethod_build_activation_factory
(self)
LHM/models/rendering/utils/renderer.py:101
↓ 1 callersFunction_build_batch_data
Inference human bounding boxes. Note: - num_bboxes: N - num_keypoints: K Args: model (nn.Module): The loaded pose mo
engine/pose_estimation/third-party/ViTPose/mmpose/apis/inference.py:298
↓ 1 callersMethod_build_dino
(model_name: str, proxy_error_retries: int = 3, proxy_error_cooldown: int = 5)
LHM/models/encoders/dino_wrapper.py:55
↓ 1 callersMethod_build_dinov2
(model_name: str, modulation_dim: int = None, pretrained: bool = True)
LHM/models/encoders/dinov2_wrapper.py:44
↓ 1 callersMethod_build_dinov2
( model_name: str, modulation_dim: int = None, pretrained: bool = True )
LHM/models/encoders/dinov2_fusion_wrapper.py:166
↓ 1 callersMethod_build_from_option
(option: str, reduction: str = 'none')
LHM/losses/pixelwise.py:32
↓ 1 callersMethod_build_layers
(self, config)
diffsynth/models/stepvideo_text_encoder.py:465
↓ 1 callersFunction_build_mlp
(nlayers, in_dim, bottleneck_dim, hidden_dim=None, use_bn=False, bias=True)
LHM/models/encoders/dinov2/layers/dino_head.py:44
↓ 1 callersFunction_build_mlp
(nlayers, in_dim, bottleneck_dim, hidden_dim=None, use_bn=False, bias=True)
engine/pose_estimation/dinov2/dinov2/layers/dino_head.py:44
↓ 1 callersMethod_build_model
(self, cfg)
lhm_runner.py:329
↓ 1 callersMethod_build_model
(self, cfg)
LHM/runners/infer/human_lrm.py:390
↓ 1 callersMethod_build_sapiens
(model_name: str, pretrained: bool = True)
LHM/models/encoders/sapiens_warpper.py:189
↓ 1 callersFunction_build_text_decoder_tower
( embed_dim, multimodal_cfg, quick_gelu: bool = False, cast_dtype: Optional[to
diffsynth/extensions/ImageQualityMetric/open_clip/coca_model.py:53
↓ 1 callersFunction_camel2snake
(s)
diffsynth/extensions/ImageQualityMetric/open_clip/hf_model.py:32
↓ 1 callersMethod_check
Check input to avoid ValueError.
engine/pose_estimation/third-party/ViTPose/mmpose/models/misc/discriminator.py:38
↓ 1 callersMethod_check_branches
Check input to avoid ValueError.
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/hrnet.py:54
↓ 1 callersMethod_check_branches
Check input to avoid ValueError.
engine/pose_estimation/third-party/ViTPose/mmpose/models/backbones/litehrnet.py:567
↓ 1 callersFunction_check_flip
Check if the origin_imgs are flipped correctly.
engine/pose_estimation/third-party/ViTPose/tests/test_pipelines/test_top_down_pipelines.py:24
↓ 1 callersFunction_check_flip
Check if the origin_imgs are flipped correctly.
engine/pose_estimation/third-party/ViTPose/tests/test_pipelines/test_hand_transform.py:9
↓ 1 callersMethod_check_heart
Check the type of Valentine Magic based on the pose results and keypoint indices of hand, mouth. and eye. Args: pred(dict
engine/pose_estimation/third-party/ViTPose/tools/webcam/webcam_apis/nodes/valentinemagic_node.py:86
↓ 1 callersFunction_check_normalize
Check if the origin_imgs are normalized correctly into result_imgs in a given norm_cfg.
engine/pose_estimation/third-party/ViTPose/tests/test_pipelines/test_top_down_pipelines.py:43
↓ 1 callersFunction_check_normalize
Check if the origin_imgs are normalized correctly into result_imgs in a given norm_cfg.
engine/pose_estimation/third-party/ViTPose/tests/test_pipelines/test_mesh_pipelines.py:40
↓ 1 callersMethod_clean
(self, text)
diffsynth/prompters/wan_prompter.py:74
↓ 1 callersFunction_clip
(pretrained=False, pretrained_name=None, model_cls=CLIP, return_transforms=False
diffsynth/models/wan_video_image_encoder.py:738
← previousnext →1,101–1,200 of 5,947, ranked by callers