MCPcopy Create free account

hub / github.com/amap-cvlab/ABot-PhysWorld / functions

Functions2,967 in github.com/amap-cvlab/ABot-PhysWorld

⨍ Functions 2,967◇ Types & classes 770↳ Endpoints 1
↓ 6 callersMethodclear_cache
(self)
inference/diffsynth/models/wan_video_vae.py:1061
↓ 6 callersFunctioncreate_custom_forward
(module)
inference/diffsynth/pipelines/wan_video_new_vace.py:1731
↓ 6 callersFunctioncreate_custom_forward
(module)
inference/diffsynth/pipelines/wan_video_new_bak.py:1557
↓ 6 callersMethoddecode
(self, t: List[int])
inference/diffsynth/prompters/kolors_prompter.py:59
↓ 6 callersMethoddecode_video
(self, latents, tiled=False, tile_size=64, tile_stride=32)
inference/diffsynth/pipelines/sd_video.py:125
↓ 6 callersMethodestimate_nnf
(self, source_guide, target_guide, source_style)
inference/diffsynth/extensions/FastBlend/patch_match.py:283
↓ 6 callersMethodgenerate
( self, image, text=None, seq_len=30, max_seq_len=77, temperat
inference/diffsynth/extensions/ImageQualityMetric/open_clip/coca_model.py:167
↓ 6 callersMethodload
(self, file_path="", state_dict={}, device="cuda", torch_dtype=torch.float16, **kwargs)
inference/diffsynth/models/model_manager.py:143
↓ 6 callersFunctionload_dimension_info
Load video list and prompt information based on a specified dimension and language from a JSON file. Parameters: - json_dir (str): The d
EZS-Bench/pbench/utils.py:208
↓ 6 callersMethodload_model
(self, file_path, model_names=None, device=None, torch_dtype=None)
inference/diffsynth/models/model_manager.py:395
↓ 6 callersMethodload_model
Load the specified VL model using vLLM
EZS-Bench/pbench/vqa_evaluation.py:97
↓ 6 callersMethodmatch
(self, file_path="", state_dict={})
inference/diffsynth/models/model_manager.py:140
↓ 6 callersFunctionmodulate
(x, shift, scale)
inference/diffsynth/models/omnigen.py:191
↓ 6 callersFunctionprecompute_freqs_cis
(dim: int, end: int = 1024, theta: float = 10000.0)
inference/diffsynth/models/wan_video_dit.py:83
↓ 6 callersMethodprocess_window_sum
(self, frames_guide, blending_table, patch_match_engine, window_size, batch_size, desc="")
inference/diffsynth/extensions/FastBlend/runners/fast.py:77
↓ 6 callersMethodremapping_table_to_blending_table
(self, table)
inference/diffsynth/extensions/FastBlend/runners/fast.py:56
↓ 6 callersFunctionrope_apply
(x, freqs, num_heads)
inference/diffsynth/models/wan_video_dit.py:92
↓ 6 callersMethodrun
(self, frames_guide, frames_style, batch_size, window_size, ebsynth_config)
inference/diffsynth/extensions/FastBlend/__init__.py:26
↓ 6 callersFunctionsave_video
(frames, save_path, fps, quality=9, ffmpeg_params=None)
inference/diffsynth/data/video.py:140
↓ 6 callersFunctionsearch_for_images
(folder)
inference/diffsynth/extensions/FastBlend/data.py:65
↓ 6 callersMethodto
(self,device)
inference/diffsynth/controlnets/processors.py:42
↓ 6 callersMethodtraining_weight
(self, timestep)
inference/diffsynth/schedulers/ddim.py:104
↓ 5 callersMethod__init__
(self, fn)
inference/diffsynth/extensions/ImageQualityMetric/trainer/models/cross_modeling.py:31
↓ 5 callersMethod__init__
(self, dim, eps=1e-6)
inference/diffsynth/models/wan_video_text_encoder.py:24
↓ 5 callersMethod__init__
( self, num_layers: int = 60, )
inference/diffsynth/models/qwen_image_dit.py:406
↓ 5 callersFunction_ntuple
(n)
inference/diffsynth/extensions/ImageQualityMetric/open_clip/utils.py:48
↓ 5 callersMethodbatch_decode
This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring o
inference/diffsynth/models/nexus_gen_ar_model.py:1083
↓ 5 callersFunctionclosest_name
(input_str, options)
inference/diffsynth/prompters/omost.py:98
↓ 5 callersMethodcontrol_noise_via_local_prompts
(self, prompt_emb_global, prompt_emb_locals, masks, mask_scales, inference_callback, special_kwargs=None, spec
inference/diffsynth/pipelines/base.py:66
↓ 5 callersMethodencode_image
(self, image, tiled=False, tile_size=64, tile_stride=32)
inference/diffsynth/pipelines/flux_image.py:194
↓ 5 callersMethodencode_video
(self, input_video, tiled=True, tile_size=(34, 34), tile_stride=(18, 16))
inference/diffsynth/pipelines/wan_video.py:276
↓ 5 callersMethodfetch_models
(self, model_manager: ModelManager, controlnet_config_units: List[ControlNetConfigUnit]=[], prompt_refiner_cla
inference/diffsynth/pipelines/sd_video.py:85
↓ 5 callersMethodfetch_tokenizer
(self, tokenizer_path=None)
inference/diffsynth/prompters/wan_prompter.py:92
↓ 5 callersFunctionget_prompt_from_filename
1. prompt-0.suffix -> prompt 2. prompt.suffix -> prompt
EZS-Bench/pbench/utils.py:388
↓ 5 callersMethodget_text_features
(self, *args, **kwargs)
inference/diffsynth/extensions/ImageQualityMetric/trainer/models/clip_model.py:110
↓ 5 callersMethodget_vram
(self)
inference/diffsynth/utils/__init__.py:130
↓ 5 callersFunctionmodulate
(x, shift=None, scale=None, tr_shift=None, tr_scale=None, tr_token=None)
inference/diffsynth/models/hunyuan_video_dit.py:285
↓ 5 callersFunctionrope_precompute
(x, grid_sizes, freqs, start=None)
inference/diffsynth/models/wan_video_dit_s2v.py:27
↓ 5 callersMethodupdate
(self, source_guide, target_guide, source_style, target_style, nnf, err, upd_nnf)
inference/diffsynth/extensions/FastBlend/patch_match.py:159
↓ 4 callersMethod__init__
(self, hidden_size, patch_size, out_channels)
inference/diffsynth/models/omnigen.py:239
↓ 4 callersMethod__init__
(self)
inference/diffsynth/models/lora.py:16
↓ 4 callersFunction_clean_tag
(tag: str)
inference/diffsynth/extensions/ImageQualityMetric/open_clip/pretrained.py:235
↓ 4 callersFunction_config_to_kwargs
(args)
inference/diffsynth/models/kolors_text_encoder.py:710
↓ 4 callersMethod_encode_image
(self, images, normalize=True)
inference/diffsynth/extensions/ImageQualityMetric/open_clip/coca_model.py:131
↓ 4 callersMethod_make_layer
(self, planes, blocks, stride=1)
inference/diffsynth/extensions/ImageQualityMetric/open_clip/modified_resnet.py:132
↓ 4 callersMethod_modulate
(self, x, mod_params)
inference/diffsynth/models/qwen_image_dit.py:356
↓ 4 callersMethod_process_attn
(self, q, k, v, shape)
inference/diffsynth/models/longcat_video_dit.py:172
↓ 4 callersFunctionapply_gate
(x, gate, tr_gate=None, tr_token=None)
inference/diffsynth/models/hunyuan_video_dit.py:394
↓ 4 callersMethodapply_nnf_to_image
(self, nnf, source)
inference/diffsynth/extensions/FastBlend/patch_match.py:44
↓ 4 callersFunctionapply_rotary_emb_qwen
( x: torch.Tensor, freqs_cis: Union[torch.Tensor, Tuple[torch.Tensor]] )
inference/diffsynth/models/qwen_image_dit.py:52
↓ 4 callersMethodcal_audio_emb
(self, audio_input, motion_frames=[73, 19])
inference/diffsynth/models/wan_video_dit_s2v.py:485
↓ 4 callersMethodclamp_bound
(self, nnf)
inference/diffsynth/extensions/FastBlend/patch_match.py:90
↓ 4 callersFunctiondownload_pretrained_from_hf
( model_id: str, filename: str = 'open_clip_pytorch_model.bin', revision=None,
inference/diffsynth/extensions/ImageQualityMetric/open_clip/pretrained.py:337
↓ 4 callersMethodenable_cpu_offload
(self)
inference/diffsynth/pipelines/base.py:91
↓ 4 callersMethodencode_prompt
(self, prompt, positive=True, t5_sequence_length=512)
inference/diffsynth/pipelines/flux_image.py:205
↓ 4 callersMethodencode_video
(self, processed_images, tiled=False, tile_size=64, tile_stride=32)
inference/diffsynth/pipelines/sd_video.py:133
↓ 4 callersMethodgelu
(self, gate: torch.Tensor)
inference/diffsynth/models/stepvideo_dit.py:576
↓ 4 callersMethodget_grid_sizes
(self, grid_size_x, grid_size_ref)
inference/diffsynth/models/wan_video_dit_s2v.py:492
↓ 4 callersMethodget_image_features
(self, *args, **kwargs)
inference/diffsynth/extensions/ImageQualityMetric/trainer/models/clip_model.py:113
↓ 4 callersFunctiongradient_checkpoint_forward
( model, use_gradient_checkpointing, use_gradient_checkpointing_offload, *args, **kwargs,
inference/diffsynth/vram_management/gradient_checkpointing.py:10
↓ 4 callersMethodinject_motion
(self, x, rope_embs, mask_input, motion_latents, drop_motion_frames=True, add_last_motion=2)
inference/diffsynth/models/wan_video_dit_s2v.py:449
↓ 4 callersFunctionlets_dance_xl
( unet: SDXLUNet, motion_modules: SDXLMotionModel = None, controlnet: MultiControlNetManager = Non
inference/diffsynth/pipelines/dancer.py:119
↓ 4 callersMethodload
(self, model: torch.nn.Module, state_dict_lora, alpha=1.0)
inference/diffsynth/lora/__init__.py:28
↓ 4 callersFunctionload_json
Load a JSON file from the given file path. Parameters: - file_path (str): The path to the JSON file. Returns: - data (dict or l
EZS-Bench/pbench/utils.py:403
↓ 4 callersFunctionload_video
Load a video from a given path and apply optional data transformations. The function supports loading video in GIF (.gif), PNG (.png), and M
EZS-Bench/pbench/utils.py:114
↓ 4 callersMethodpad_image
(self, image)
inference/diffsynth/extensions/FastBlend/patch_match.py:38
↓ 4 callersMethodpatch_multiple_resolutions
(self, latents, padding_latent=None, is_input_images:bool=False)
inference/diffsynth/models/omnigen.py:451
↓ 4 callersMethodpreprocess
(self, controlnet_inputs: list[ControlNetInput], conditionings: list[torch.Tensor], **kwargs)
inference/diffsynth/pipelines/qwen_image.py:29
↓ 4 callersMethodprocess
(self, pipe: BasePipeline, inputs: dict, positive=True, **kwargs)
inference/diffsynth/utils/__init__.py:242
↓ 4 callersMethodprocess_entity_masks
(self, hidden_states, prompt_emb, entity_prompt_emb, entity_masks, text_ids, image_ids, repeat_dim)
inference/diffsynth/models/flux_dit.py:378
↓ 4 callersMethodprocess_mllm_input
(self, mllm_inputs, target_img_size)
inference/diffsynth/prompters/omnigen_prompter.py:259
↓ 4 callersMethodreturn_to_timestep
(self, timestep, sample, sample_stablized)
inference/diffsynth/schedulers/ddim.py:81
↓ 4 callersFunctionsafe_str
(x)
inference/diffsynth/prompters/omost.py:95
↓ 4 callersMethodset_full_adapter
(self)
inference/diffsynth/models/sd_ipadapter.py:26
↓ 4 callersMethodshape
(self)
inference/diffsynth/extensions/FastBlend/data.py:129
↓ 4 callersMethodunpatchify
x: (N, T, patch_size**2 * C) imgs: (N, H, W, C)
inference/diffsynth/models/omnigen.py:413
↓ 3 callersMethod__getitem__
(self, item)
inference/diffsynth/data/video.py:122
↓ 3 callersMethod__init__
(self)
inference/diffsynth/vram_management/layers.py:12
↓ 3 callersMethod__init__
(self, num_feat, num_grow_ch=32)
inference/diffsynth/extensions/ESRGAN/__init__.py:29
↓ 3 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
inference/diffsynth/extensions/ImageQualityMetric/BLIP/vit.py:22
↓ 3 callersMethod__init__
( self, in_channels: int = 3, out_channels: int = 16, eps=1e-6, dropou
inference/diffsynth/models/hunyuan_video_vae_encoder.py:70
↓ 3 callersMethod__init__
(self, disable_guidance_embedder=False, num_joint_blocks=5, num_single_blocks=10, num_mode=0, mode_dict={}, ad
inference/diffsynth/models/flux_controlnet.py:9
↓ 3 callersMethod__init__
(self)
inference/diffsynth/models/cog_dit.py:109
↓ 3 callersMethod__init__
(self)
inference/diffsynth/models/sdxl_ipadapter.py:44
↓ 3 callersMethod__len__
(self)
inference/diffsynth/data/video.py:109
↓ 3 callersFunction_build_text_tower
( embed_dim: int, text_cfg: CLIPTextCfg, quick_gelu: bool = False, cast_dtype:
inference/diffsynth/extensions/ImageQualityMetric/open_clip/model.py:137
↓ 3 callersFunction_build_vision_tower
( embed_dim: int, vision_cfg: CLIPVisionCfg, quick_gelu: bool = False, cast_dt
inference/diffsynth/extensions/ImageQualityMetric/open_clip/model.py:75
↓ 3 callersMethodafter_patch_embedding
(self, x: List[torch.Tensor], pose_latents, face_pixel_values)
inference/diffsynth/models/wan_video_animate_adapter.py:623
↓ 3 callersFunctionapply_gate
AI is creating summary for apply_gate Args: x (torch.Tensor): input tensor. gate (torch.Tensor, optional): gate tensor. Defaults
inference/diffsynth/models/step1x_connector.py:170
↓ 3 callersFunctionapply_rotary_emb
( xq: torch.Tensor, xk: torch.Tensor, freqs_cis, head_first: bool = False, )
inference/diffsynth/models/hunyuan_video_dit.py:354
↓ 3 callersFunctionbase_conv3d
(x, conv_layer, channel_last=False, residual=None, only_return_output=False)
inference/diffsynth/models/stepvideo_vae.py:74
↓ 3 callersFunctionbase_group_norm
(x, norm_layer, act_silu=False, channel_last=False)
inference/diffsynth/models/stepvideo_vae.py:32
↓ 3 callersFunctionbase_group_norm_with_zero_pad
(x, norm_layer, act_silu=True, pad_size=2)
inference/diffsynth/models/stepvideo_vae.py:405
↓ 3 callersFunctionbasic_clean
(text)
inference/diffsynth/prompters/wan_prompter.py:11
↓ 3 callersMethodbuild_1d_mask
(self, length, left_bound, right_bound, border_width)
inference/diffsynth/models/hunyuan_video_vae_decoder.py:408
↓ 3 callersMethodbuild_1d_mask
(self, length, left_bound, right_bound, border_width)
inference/diffsynth/models/hunyuan_video_vae_encoder.py:207
↓ 3 callersMethodbuild_chat_input
(self, query, history=None, role="user")
inference/diffsynth/prompters/kolors_prompter.py:203
↓ 3 callersFunctioncalc_out_
(in_size, padding, dilation, kernel, stride)
inference/diffsynth/models/stepvideo_vae.py:115
↓ 3 callersMethodcheck_free_vram
(self)
inference/diffsynth/vram_management/layers.py:15
↓ 3 callersFunctionclip_transform
(n_px)
EZS-Bench/pbench/utils.py:39
← previousnext →101–200 of 2,967, ranked by callers