MCPcopy Create free account

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

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

⨍ Functions 1,933◇ Types & classes 464↳ Endpoints 1
↓ 458 callersMethodto
(self, *args, **kwargs)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:85
↓ 290 callersMethodfrom_pretrained
( torch_dtype: torch.dtype = torch.bfloat16, device: Union[str, torch.device] = "cuda",
DiffSynth-Studio/diffsynth/pipelines/z_image.py:43
↓ 237 callersMethodcat
(self, new_stats: "MaskData")
VideoCus-Factory/sam2/utils/amg.py:61
↓ 179 callersFunctionsave_video
(frames, save_path, fps, quality=9, ffmpeg_params=None)
DiffSynth-Studio/diffsynth/utils/data/__init__.py:140
↓ 100 callersMethodload_lora
( self, module: torch.nn.Module, lora_config: Union[ModelConfig, str] = None,
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:231
↓ 77 callersFunctionload_state_dict
(file_path, torch_dtype=None, device="cpu")
DiffSynth-Studio/diffsynth/core/loader/file.py:5
↓ 60 callersMethodload_models_to_device
(self, model_names)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:146
↓ 57 callersMethoditems
(self)
VideoCus-Factory/sam2/utils/amg.py:43
↓ 42 callersMethodfetch_model
(self, model_name, index=None)
DiffSynth-Studio/diffsynth/models/model_loader.py:82
↓ 38 callersMethodupdate
(self, hidden_states)
DiffSynth-Studio/diffsynth/pipelines/wan_video.py:1063
↓ 35 callersMethodpreprocess_image
(self, image, torch_dtype=None, device=None, pattern="B C H W", min_value=-1, max_value=1)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:112
↓ 33 callersMethodnorm
(self, x)
DiffSynth-Studio/diffsynth/models/wan_video_dit.py:105
↓ 31 callersMethodencode
Encode a batch of images into latents. Args: x (`torch.Tensor`): Input batch of images. return_dict (`bool`,
DiffSynth-Studio/diffsynth/models/flux2_vae.py:2057
↓ 28 callersMethodload
(self, model: torch.nn.Module, state_dict_lora, alpha=1.0)
DiffSynth-Studio/diffsynth/models/flux_lora_patcher.py:123
↓ 26 callersMethodkeys
(self)
DiffSynth-Studio/diffsynth/core/vram/disk_map.py:18
↓ 24 callersMethod__init__
(self, num_inference_steps, rel_l1_thresh, model_id)
DiffSynth-Studio/diffsynth/pipelines/wan_video.py:1017
↓ 24 callersMethod_append_dbg
(self, s: str)
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B_tensor_parallel.py:93
↓ 20 callersMethod__init__
(self, num_inference_steps, rel_l1_thresh)
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:908
↓ 20 callersMethoddevice
(self)
VideoCus-Factory/sam2/modeling/sam2_base.py:192
↓ 17 callersMethod__init__
( self, in_channels: int, out_channels: int, factor_t, factor_s=1,
DiffSynth-Studio/diffsynth/models/wan_video_vae.py:399
↓ 17 callersMethod__init__
(self, kernel, pad, upsample_factor=1)
DiffSynth-Studio/diffsynth/models/wan_video_animate_adapter.py:370
↓ 16 callersMethodpreprocess_video
(self, video, torch_dtype=None, device=None, pattern="B C T H W", min_value=-1, max_value=1)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:121
↓ 16 callersMethodraw_data
(self)
DiffSynth-Studio/diffsynth/utils/data/__init__.py:96
↓ 15 callersMethoddownload_if_necessary
(self)
DiffSynth-Studio/diffsynth/core/loader/config.py:95
↓ 15 callersMethodto
(self,device)
DiffSynth-Studio/diffsynth/utils/controlnet/annotator.py:42
↓ 14 callersFunctioncreate_custom_forward
(module)
DiffSynth-Studio/diffsynth/pipelines/wan_video.py:1319
↓ 13 callersMethod__init__
(self, device="cuda", torch_dtype=torch.bfloat16)
DiffSynth-Studio/diffsynth/pipelines/qwen_image.py:25
↓ 12 callersMethod__init__
( self, patch_size: int = 1, in_channels: int = 128, out_channels: Optional[in
DiffSynth-Studio/diffsynth/models/flux2_dit.py:870
↓ 12 callersMethodprocess
(self, pipe, **kwargs)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:52
↓ 12 callersMethodrope_params
Args: index: [0, 1, 2, 3] 1D Tensor representing the position index of the token
DiffSynth-Studio/diffsynth/models/qwen_image_dit.py:80
↓ 11 callersFunctionFlowMatchSFTLoss
(pipe: BasePipeline, **inputs)
DiffSynth-Studio/diffsynth/diffusion/loss.py:5
↓ 11 callersMethod__init__
(self, embed_dim=512, image_size=224, patch_size=16,
DiffSynth-Studio/diffsynth/models/wan_video_image_encoder.py:483
↓ 11 callersMethod__init__
( self, dim: int, num_heads: int, enable_flashattn3: bool = False, ena
DiffSynth-Studio/diffsynth/models/longcat_video_dit.py:138
↓ 11 callersMethodset_timesteps
(self, num_inference_steps=100, denoising_strength=1.0, training=False, **kwargs)
DiffSynth-Studio/diffsynth/diffusion/flow_match.py:132
↓ 10 callersFunctionDirectDistillLoss
(pipe: BasePipeline, **inputs)
DiffSynth-Studio/diffsynth/diffusion/loss.py:24
↓ 10 callersMethod_register_one_time_hook
注册 forward hook：只记录一次输出信息到 txt.
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B_tensor_parallel.py:128
↓ 10 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-14B_tensor_parallel_all_reverse.py:61
↓ 10 callersMethodpredict
Predict masks for the given input prompts, using the currently set image. Arguments: point_coords (np.ndarray or None): A
VideoCus-Factory/sam2/sam2_image_predictor.py:237
↓ 10 callersMethodreshape_heads_to_batch_dim
(self, tensor)
Video-Depth-Anything/video_depth_anything/motion_module/attention.py:93
↓ 10 callersMethodstep
(self, scheduler, latents, progress_id, noise_pred, input_latents=None, inpaint_mask=None, **kwargs)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:209
↓ 9 callersMethod__init__
( self, in_channels: int = 3, out_channels: int = 3, down_block_types: Tuple[s
DiffSynth-Studio/diffsynth/models/flux2_vae.py:1650
↓ 9 callersMethod__init__
( self, base_dim: int = 96, z_dim: int = 16, dim_mult: Tuple[int] = [1, 2, 4,
DiffSynth-Studio/diffsynth/models/qwen_image_vae.py:643
↓ 9 callersFunctiongradient_checkpoint_forward
( model, use_gradient_checkpointing, use_gradient_checkpointing_offload, *args, **kwargs,
DiffSynth-Studio/diffsynth/core/gradient/gradient_checkpoint.py:10
↓ 9 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_training/validate_full/Wan2.2-VACE-Fun-A14B_tensor_parallel_all.py:61
↓ 9 callersMethodpatchify
(self, hidden_states)
DiffSynth-Studio/diffsynth/models/flux_dit.py:296
↓ 8 callersMethod__init__
( self, in_channels, hidden_channels=None, out_features=None, act_laye
DiffSynth-Studio/diffsynth/models/step1x_connector.py:25
↓ 8 callersMethod__init__
(self, in_dim, out_dim, has_pos_emb=False)
DiffSynth-Studio/diffsynth/models/wan_video_dit.py:233
↓ 8 callersMethodfilter
(self, keep: torch.Tensor)
VideoCus-Factory/sam2/utils/amg.py:46
↓ 8 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-14B_tensor_parallel_all.py:61
↓ 8 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-1.3B_tensor_parallel_all.py:61
↓ 8 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_training/validate_full/Wan2.2-VACE-Fun-A14B_tensor_parallel.py:64
↓ 8 callersFunctionrun_inference
(script_path)
DiffSynth-Studio/examples/dev_tools/unit_test.py:21
↓ 8 callersFunctionsave_video_with_audio
(frames, save_path, audio_path, fps=16, quality=9, ffmpeg_params=None)
DiffSynth-Studio/diffsynth/utils/data/__init__.py:215
↓ 8 callersMethodupdate
(self, hidden_states)
DiffSynth-Studio/diffsynth/pipelines/flux_image.py:945
↓ 7 callersMethod__init__
(self, q_dim, num_heads, head_dim, kv_dim=None, bias_q=False, bias_kv=False, bias_out=False)
DiffSynth-Studio/diffsynth/models/flux_vae.py:155
↓ 7 callersMethod__init__
(self, disable_guidance_embedder=False, input_dim=64, num_blocks=19)
DiffSynth-Studio/diffsynth/models/flux_dit.py:278
↓ 7 callersMethodafter_transformer_block
(self, block_idx, hidden_states, audio_emb_global, audio_emb, original_seq_len, use_unified_sequence_parallel=
DiffSynth-Studio/diffsynth/models/wan_video_dit_s2v.py:459
↓ 7 callersMethodcfg_guided_model_fn
(self, model_fn, cfg_scale, inputs_shared, inputs_posi, inputs_nega, **inputs_others)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:306
↓ 7 callersFunctioncheck_is_instance
(model, module_class)
DiffSynth-Studio/diffsynth/models/wan_video_vae.py:11
↓ 7 callersFunctionexample
(pipe, seeds, example_id, global_prompt, entity_prompts)
DiffSynth-Studio/examples/flux/model_inference/FLUX.1-dev-EliGen.py:65
↓ 7 callersFunctionexample
(pipe, seeds, example_id, global_prompt, entity_prompts)
DiffSynth-Studio/examples/flux/model_inference_low_vram/FLUX.1-dev-EliGen.py:75
↓ 7 callersFunctionflash_attention
(q: torch.Tensor, k: torch.Tensor, v: torch.Tensor, num_heads: int, compatibility_mode=False)
DiffSynth-Studio/diffsynth/models/wan_video_dit.py:27
↓ 7 callersMethodgelu
(self, gate)
Video-Depth-Anything/video_depth_anything/motion_module/attention.py:350
↓ 7 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-1.3B_tensor_parallel.py:62
↓ 7 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_training/validate_full/Wan2.1-VACE-14B_tensor_parallel.py:62
↓ 7 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.1-VACE-14B_tensor_parallel.py:55
↓ 7 callersFunctionmodulate
(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor)
DiffSynth-Studio/diffsynth/models/wan_video_dit.py:63
↓ 7 callersFunctionrun_train_single_GPU
(script_path)
DiffSynth-Studio/examples/dev_tools/unit_test.py:65
↓ 7 callersMethodset_processor
r""" Set the attention processor to use. Args: processor (`AttnProcessor`): The attention processor to us
DiffSynth-Studio/diffsynth/models/flux2_vae.py:917
↓ 7 callersFunctionsinusoidal_embedding_1d
(dim, position)
DiffSynth-Studio/diffsynth/models/wan_video_dit.py:67
↓ 6 callersMethod__init__
(self, config)
DiffSynth-Studio/diffsynth/models/nexus_gen_projector.py:182
↓ 6 callersMethod__init__
( self, dim: int, in_dim: int, ffn_dim: int, out_dim: int, tex
DiffSynth-Studio/diffsynth/models/wan_video_dit_s2v.py:361
↓ 6 callersMethod__init__
( self, num_layers: int = 60, use_layer3d_rope: bool = False, use_additional_t
DiffSynth-Studio/diffsynth/models/qwen_image_dit.py:552
↓ 6 callersMethod_separate_heads
(self, x: Tensor, num_heads: int)
VideoCus-Factory/sam2/modeling/sam/transformer.py:220
↓ 6 callersMethodadd_noise
(self, original_samples, noise, timestep)
DiffSynth-Studio/diffsynth/diffusion/flow_match.py:164
↓ 6 callersFunctionapply_rotary_emb
Apply rotary embeddings to input tensors using the given frequency tensor. This function applies rotary embeddings to the given query or key
DiffSynth-Studio/diffsynth/models/flux2_dit.py:241
↓ 6 callersMethodclear_cache
(self)
DiffSynth-Studio/diffsynth/models/wan_video_vae.py:1048
↓ 6 callersMethodconstrain_to_multiple_of
(self, x, min_val=0, max_val=None)
Video-Depth-Anything/video_depth_anything/util/transform.py:51
↓ 6 callersMethodgenerate_noise
(self, shape, seed=None, rand_device="cpu", rand_torch_dtype=torch.float32, device=None, torch_dtype=None)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:171
↓ 6 callersFunctionprecompute_freqs_cis
(dim: int, end: int = 1024, theta: float = 10000.0)
DiffSynth-Studio/diffsynth/models/wan_video_dit.py:82
↓ 6 callersFunctionrope_apply
(x, freqs, num_heads)
DiffSynth-Studio/diffsynth/models/wan_video_dit.py:91
↓ 6 callersMethodrope_params
Args: index: [0, 1, 2, 3] 1D Tensor representing the position index of the token
DiffSynth-Studio/diffsynth/models/qwen_image_dit.py:254
↓ 6 callersFunctionsave_video
(frames, output_video_path, fps=10, is_depths=False)
Video-Depth-Anything/utils/dc_utils.py:72
↓ 6 callersMethodswitch_pipe_to_training_mode
( self, pipe, trainable_models=None, lora_base_model=None, lora_target_modules
DiffSynth-Studio/diffsynth/diffusion/training_module.py:140
↓ 6 callersMethodvae_output_to_image
(self, vae_output, pattern="B C H W", min_value=-1, max_value=1)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:128
↓ 5 callersMethod__init__
(self, device="cuda", torch_dtype=torch.bfloat16)
DiffSynth-Studio/diffsynth/pipelines/flux2_image.py:21
↓ 5 callersMethod__init__
(self, dim, eps=1e-6)
DiffSynth-Studio/diffsynth/models/wan_video_text_encoder.py:27
↓ 5 callersMethod__init__
(self, q_dim, num_heads, head_dim, kv_dim=None, bias_q=False, bias_kv=False, bias_out=False)
DiffSynth-Studio/diffsynth/models/flux_lora_encoder.py:17
↓ 5 callersMethod__init__
(self, q_dim, num_heads, head_dim, kv_dim=None, bias_q=False, bias_kv=False, bias_out=False)
DiffSynth-Studio/diffsynth/models/z_image_dit.py:74
↓ 5 callersFunctionadd_general_config
(parser: argparse.ArgumentParser)
DiffSynth-Studio/diffsynth/diffusion/parsers.py:63
↓ 5 callersMethodcheck_resize_height_width
(self, height, width, num_frames=None)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:95
↓ 5 callersMethodcheck_vram_management_state
(self)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:298
↓ 5 callersMethoddecode
( self, z: torch.FloatTensor, return_dict: bool = True, generator=None )
DiffSynth-Studio/diffsynth/models/flux2_vae.py:2102
↓ 5 callersMethoddefault_image_operator
( base_path="", max_pixels=1920*1080, height=None, width=None, height_division_factor=
DiffSynth-Studio/diffsynth/core/data/unified_dataset.py:29
↓ 5 callersMethoddownload_and_load_models
(self, model_configs: list[ModelConfig] = [], vram_limit: float = None)
DiffSynth-Studio/diffsynth/diffusion/base_pipeline.py:282
↓ 5 callersMethodencode_image
(self, videos)
DiffSynth-Studio/diffsynth/models/wan_video_image_encoder.py:864
↓ 5 callersMethodimport_model_class
(self, model_class)
DiffSynth-Studio/diffsynth/models/model_loader.py:13
↓ 5 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B_tensor_parallel_v2.py:56
↓ 5 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.1-VACE-1.3B_sequence_parallel.py:19
↓ 5 callersFunctionis_rank0
()
DiffSynth-Studio/examples/wanvideo/model_inference/Wan2.2-VACE-Fun-A14B_tensor_parallel.py:55
next →1–100 of 1,933, ranked by callers