MCPcopy Create free account

hub / github.com/caiyuanhao1998/Open-OmniVCus / functions

Functions1,933 in github.com/caiyuanhao1998/Open-OmniVCus

↓ 1 callersMethodcompute_empirical_mu
(image_seq_len, num_steps)
DiffSynth-Studio/diffsynth/diffusion/flow_match.py:74
↓ 1 callersMethodcompute_freqs_mot
(self, f, h, w, end: int = 1024, theta: float = 10000.0)
DiffSynth-Studio/diffsynth/models/wan_video_mot.py:146
↓ 1 callersMethodcompute_regularization
(self, pipe: BasePipeline, trajectory_teacher, inputs_shared, inputs_posi, inputs_nega, num_inference_steps, c
DiffSynth-Studio/diffsynth/diffusion/loss.py:91
↓ 1 callersFunctioncompute_scale
(prediction, target, mask)
Video-Depth-Anything/utils/util.py:23
↓ 1 callersFunctioncompute_scale_and_shift
(prediction, target, mask, scale_only=False)
Video-Depth-Anything/utils/util.py:16
↓ 1 callersFunctioncompute_scale_and_shift_full
(prediction, target, mask)
Video-Depth-Anything/utils/util.py:40
↓ 1 callersFunctionconcat_points
Add new points and labels to previous point inputs (add at the end).
VideoCus-Factory/sam2/utils/misc.py:319
↓ 1 callersFunctionconstruct_demo
()
Video-Depth-Anything/app.py:62
↓ 1 callersMethodconstruct_mask
(self, entity_masks, prompt_seq_len, image_seq_len)
DiffSynth-Studio/diffsynth/models/flux_dit.py:323
↓ 1 callersFunctionconvert_keys_dict_to_single_str
(state_dict, with_shape=True)
DiffSynth-Studio/diffsynth/core/loader/file.py:101
↓ 1 callersMethodconvert_state_dict
(self, state_dict, suffix=".weight")
DiffSynth-Studio/diffsynth/utils/lora/general.py:33
↓ 1 callersFunctionconvert_state_dict_to_keys_dict
(state_dict)
DiffSynth-Studio/diffsynth/core/loader/file.py:85
↓ 1 callersFunctioncrop_and_resize
(image, height, width)
DiffSynth-Studio/diffsynth/utils/data/__init__.py:67
↓ 1 callersMethodcrop_and_resize
(self, image, target_height, target_width)
DiffSynth-Studio/diffsynth/core/data/operators.py:75
↓ 1 callersFunctioncsv_out_paths
(csv_path: str)
VideoCus-Factory/data_augmentation.py:230
↓ 1 callersFunctioncustom_meshgrid
(*args)
DiffSynth-Studio/diffsynth/models/wan_video_camera_controller.py:109
↓ 1 callersFunctioncustom_qr
(input_tensor)
DiffSynth-Studio/diffsynth/models/wan_video_animate_adapter.py:314
↓ 1 callersFunctiondecomposite
(tensor_A, tensor_B, rank)
DiffSynth-Studio/diffsynth/utils/lora/reset_rank.py:3
↓ 1 callersMethoddefault_lora_patterns
(self)
DiffSynth-Studio/diffsynth/models/flux_lora_encoder.py:449
↓ 1 callersMethoddefault_lora_patterns
(self)
DiffSynth-Studio/diffsynth/models/flux_lora_patcher.py:284
↓ 1 callersMethoddefault_video_operator
( base_path="", max_pixels=1920*1080, height=None, width=None, height_division_factor=
DiffSynth-Studio/diffsynth/core/data/unified_dataset.py:40
↓ 1 callersMethoddefault_vram_config
(self)
DiffSynth-Studio/diffsynth/models/model_loader.py:49
↓ 1 callersFunctiondemo_coarse_fine_bias
()
DiffSynth-Studio/examples/qwen_image/model_inference/Qwen-Image-i2L.py:47
↓ 1 callersFunctiondemo_coarse_fine_bias
()
DiffSynth-Studio/examples/qwen_image/model_inference_low_vram/Qwen-Image-i2L.py:69
↓ 1 callersFunctiondemo_style
()
DiffSynth-Studio/examples/qwen_image/model_inference/Qwen-Image-i2L.py:13
↓ 1 callersFunctiondemo_style
()
DiffSynth-Studio/examples/qwen_image/model_inference_low_vram/Qwen-Image-i2L.py:34
↓ 1 callersFunctiondepth_of_frame
frame_rgb_uint8: (H,W,3) uint8 out_hw: (H,W) target size for depth map return: (H,W) uint8 depth (0..255)
VideoCus-Factory/process_data_depth.py:78
↓ 1 callersMethoddisable_all_loras
(self)
DiffSynth-Studio/diffsynth/models/longcat_video_dit.py:745
↓ 1 callersFunctiondist_barrier
()
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B_tensor_parallel_v2.py:68
↓ 1 callersFunctiondist_barrier
()
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.1-VACE-14B_tensor_parallel.py:67
↓ 1 callersFunctiondist_barrier
()
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.2-VACE-Fun-A14B_tensor_parallel.py:67
↓ 1 callersMethoddownload
(self)
DiffSynth-Studio/diffsynth/core/loader/config.py:60
↓ 1 callersFunctiondrop_path
(x, drop_prob: float = 0.0, training: bool = False)
Video-Depth-Anything/video_depth_anything/dinov2_layers/drop_path.py:15
↓ 1 callersMethodenable_usp
(self)
DiffSynth-Studio/diffsynth/pipelines/wan_video.py:84
↓ 1 callersFunctionenable_vram_management_recursively
(model: torch.nn.Module, module_map: dict, vram_config: dict, vram_limit=None, name_prefix="", disk_map=None,
DiffSynth-Studio/diffsynth/core/vram/layers.py:439
↓ 1 callersMethodencode_images
(self, pipe: QwenImagePipeline, images: list[Image.Image])
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:630
↓ 1 callersMethodencode_images_using_dinov3
(self, pipe: QwenImagePipeline, images: list[Image.Image])
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:612
↓ 1 callersMethodencode_images_using_siglip2
(self, pipe: QwenImagePipeline, images: list[Image.Image])
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:603
↓ 1 callersMethodencode_prompt
( self, pipe, prompt: Union[str, List[str]], device: Optional[torch.device] =
DiffSynth-Studio/diffsynth/pipelines/z_image.py:152
↓ 1 callersMethodencode_prompt
( self, text_encoder, tokenizer, prompt: Union[str, List[str]], dtype
DiffSynth-Studio/diffsynth/pipelines/flux2_image.py:243
↓ 1 callersMethodencode_prompt
( self, tokenizer_1, tokenizer_2, text_encoder_1, text_encoder_2,
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:372
↓ 1 callersMethodencode_prompt
( self, tokenizer_1, tokenizer_2, text_encoder_1, text_encoder_2,
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:553
↓ 1 callersMethodencode_prompt
(self, pipe: WanVideoPipeline, prompt)
DiffSynth-Studio/diffsynth/pipelines/wan_video.py:404
↓ 1 callersMethodencode_prompt
(self, pipe: QwenImagePipeline, prompt)
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:348
↓ 1 callersMethodencode_prompt_edit
(self, pipe: QwenImagePipeline, prompt, edit_image)
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:360
↓ 1 callersMethodencode_prompt_edit
(self, pipe: QwenImagePipeline, prompt, edit_image)
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:589
↓ 1 callersMethodencode_prompt_edit_multi
(self, pipe: QwenImagePipeline, prompt, edit_image)
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:370
↓ 1 callersMethodencode_prompt_using_clip
(self, prompt, text_encoder, tokenizer, max_length, device)
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:350
↓ 1 callersMethodencode_prompt_using_clip
(self, prompt, text_encoder, tokenizer, max_length, device)
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:531
↓ 1 callersMethodencode_prompt_using_t5
(self, prompt, text_encoder, tokenizer, max_length, device)
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:361
↓ 1 callersMethodencode_prompt_using_t5
(self, prompt, text_encoder, tokenizer, max_length, device)
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:542
↓ 1 callersFunctionexample
(pipe, seeds, example_id, global_prompt, entity_prompts, height=784, width=1280)
DiffSynth-Studio/examples/qwen_image/model_inference/Qwen-Image-EliGen-Poster.py:66
↓ 1 callersFunctionexample
(pipe, seeds, example_id, global_prompt, entity_prompts, height=784, width=1280)
DiffSynth-Studio/examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen-Poster.py:66
↓ 1 callersMethodextract_arcface_bgr_embedding
(self, in_image, landmark, device)
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:821
↓ 1 callersMethodextract_audio_feat
(self, input_audio, sample_rate, processor, return_all_layers=False, dtype=torch.float32, device='cpu')
DiffSynth-Studio/diffsynth/models/wav2vec.py:102
↓ 1 callersFunctionextract_keys
(input_json, output_json, keys=("original", "vid"))
VideoCus-Factory/json_extract.py:6
↓ 1 callersMethodextract_masked_hidden
(self, hidden_states: torch.Tensor, mask: torch.Tensor)
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:412
↓ 1 callersMethodextract_masked_hidden
(self, hidden_states: torch.Tensor, mask: torch.Tensor)
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:582
↓ 1 callersMethodfetch_module_map
(self, model_class, vram_config)
DiffSynth-Studio/diffsynth/models/model_loader.py:22
↓ 1 callersMethodfetch_rename_dict
(self, state_dict_converter)
DiffSynth-Studio/diffsynth/core/vram/disk_map.py:73
↓ 1 callersMethodfetch_trajectory
(self, pipe: BasePipeline, timesteps_student, inputs_shared, inputs_posi, inputs_nega, num_inference_steps, cf
DiffSynth-Studio/diffsynth/diffusion/loss.py:46
↓ 1 callersFunctionfill_holes_in_mask_scores
A post processor to fill small holes in mask scores with area under `max_area`.
VideoCus-Factory/sam2/utils/misc.py:290
↓ 1 callersFunctionfill_vram_config
(model, vram_config)
DiffSynth-Studio/diffsynth/core/vram/layers.py:455
↓ 1 callersFunctionflash_attention_2
(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s
DiffSynth-Studio/diffsynth/core/attention/attention.py:84
↓ 1 callersFunctionflash_attention_3
(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, q_pattern="b n s d", k_pattern="b n s d", v_pattern="b n s
DiffSynth-Studio/diffsynth/core/attention/attention.py:74
↓ 1 callersFunctionflow_to_color
将光流 (H, W, 2) 转换为颜色编码图。 参数: - flow: numpy.ndarray, 光流张量,形状为 (H, W, 2),值范围为 [-1, 1] - max_flow: float, 光流的最大值,用于归一化 (默认假设范围是 [-1,
VideoCus-Factory/track_to_map.py:95
↓ 1 callersFunctionflux2_parser
()
DiffSynth-Studio/examples/flux2/model_training/train.py:83
↓ 1 callersFunctionflux_parser
()
DiffSynth-Studio/examples/flux/model_training/train.py:86
↓ 1 callersMethodformat_text_input
(self, prompts: List[str], system_message: str = None)
DiffSynth-Studio/diffsynth/pipelines/flux2_image.py:153
↓ 1 callersMethodforward
(self, sample, tiled=False, tile_size=64, tile_stride=32, **kwargs)
DiffSynth-Studio/diffsynth/models/flux_vae.py:344
↓ 1 callersMethodforward
(self, sample, tiled=False, tile_size=64, tile_stride=32, **kwargs)
DiffSynth-Studio/diffsynth/models/flux_vae.py:412
↓ 1 callersMethodforward
( self, x, vace_context, context, t_mod, freqs, use_gradient_checkpointing: bool = False,
DiffSynth-Studio/diffsynth/models/wan_video_vace.py:53
↓ 1 callersMethodforward
(self, x)
Video-Depth-Anything/video_depth_anything/video_depth.py:58
↓ 1 callersMethodforward
(self, x: Tensor)
Video-Depth-Anything/video_depth_anything/dinov2_layers/block.py:82
↓ 1 callersMethodforward
(self, x: Tensor)
Video-Depth-Anything/video_depth_anything/dinov2_layers/attention.py:49
↓ 1 callersMethodforward_batch
(self, img_list)
VideoCus-Factory/sam2/utils/transforms.py:41
↓ 1 callersMethodforward_features
(self, x, masks=None)
Video-Depth-Anything/video_depth_anything/dinov2.py:253
↓ 1 callersMethodforward_features_list
(self, x_list, masks_list)
Video-Depth-Anything/video_depth_anything/dinov2.py:233
↓ 1 callersMethodforward_nested
x_list contains a list of tensors to nest together and run
Video-Depth-Anything/video_depth_anything/dinov2_layers/block.py:205
↓ 1 callersMethodforward_sampling
(self, video_fhw, txt_seq_lens, device)
DiffSynth-Studio/diffsynth/models/qwen_image_dit.py:168
↓ 1 callersMethodforward_with_kv_cache
DiffSynth-Studio/diffsynth/models/longcat_video_dit.py:222
↓ 1 callersMethodfp8_linear
( self, input: torch.Tensor, weight: torch.Tensor, bias: torch.Tensor = None,
DiffSynth-Studio/diffsynth/core/vram/layers.py:321
↓ 1 callersMethodfreeze_except
(self, model_names)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:193
↓ 1 callersMethodfrom_diffusers
(self, state_dict)
DiffSynth-Studio/diffsynth/models/flux_controlnet.py:269
↓ 1 callersMethodfrom_diffusers
(self, state_dict)
DiffSynth-Studio/diffsynth/models/flux_ipadapter.py:99
↓ 1 callersMethodfuse_lora_to_base_model
(self, model: torch.nn.Module, state_dict_lora, alpha=1.0)
DiffSynth-Studio/diffsynth/utils/lora/flux.py:81
↓ 1 callersMethodgelu
(self, gate)
Video-Depth-Anything/video_depth_anything/motion_module/attention.py:376
↓ 1 callersMethodgenerate
Generates masks for the given image. Arguments: image (np.ndarray): The image to generate masks for, in HWC uint8 format.
VideoCus-Factory/sam2/automatic_mask_generator.py:170
↓ 1 callersFunctiongenerate_camera_coordinates
( direction: Literal["Left", "Right", "Up", "Down", "LeftUp", "LeftDown", "RightUp", "RightDown", "In", "O
DiffSynth-Studio/diffsynth/models/wan_video_camera_controller.py:184
↓ 1 callersFunctiongenerate_crop_boxes
Generates a list of crop boxes of different sizes. Each layer has (2**i)**2 boxes for the ith layer.
VideoCus-Factory/sam2/utils/amg.py:202
↓ 1 callersFunctionget_1d_rotary_pos_embed
Precompute the frequency tensor for complex exponentials (cis) with given dimensions. This function calculates a frequency tensor with compl
DiffSynth-Studio/diffsynth/models/flux2_dit.py:174
↓ 1 callersFunctionget_1d_sine_pe
Get 1D sine positional embedding as in the original Transformer paper.
VideoCus-Factory/sam2/modeling/sam2_utils.py:60
↓ 1 callersFunctionget_activation
Helper function to get activation function from string. Args: act_fn (str): Name of activation function. Returns: nn.Module:
DiffSynth-Studio/diffsynth/models/flux2_vae.py:31
↓ 1 callersFunctionget_activation_fn
Return an activation function given a string
VideoCus-Factory/sam2/modeling/sam2_utils.py:73
↓ 1 callersMethodget_audio_embed_bucket_fps
(self, audio_embed, fps=16, batch_frames=81, m=0)
DiffSynth-Studio/diffsynth/models/wav2vec.py:147
↓ 1 callersMethodget_audio_feats_per_inference
(self, input_audio, sample_rate, processor, fps=16, batch_frames=80, m=0, dtype=torch.float32, device='cpu')
DiffSynth-Studio/diffsynth/models/wav2vec.py:186
↓ 1 callersFunctionget_branges_scales
(x, sample_drop_ratio=0.0)
Video-Depth-Anything/video_depth_anything/dinov2_layers/block.py:134
↓ 1 callersFunctionget_cropped_flows
trajs: (B, N, T, 2) in pixel coords returns: (C, n_frames_out, H, W) in [-1,1] We always generate exactly n_frames_out frames for output
VideoCus-Factory/track_to_map_local.py:61
↓ 1 callersFunctionget_cropped_flows
( trajs: torch.Tensor, keep_min_prob: float = 0.0, keep_max_prob: float = 1.0, n_frames: int =
VideoCus-Factory/track_to_map.py:159
↓ 1 callersMethodget_default_image_grid_thw
(self,)
DiffSynth-Studio/diffsynth/models/nexus_gen_ar_model.py:734
← previousnext →501–600 of 1,933, ranked by callers