MCPcopy Create free account

hub / github.com/Netflix/void-model / functions

Functions673 in github.com/Netflix/void-model

↓ 1 callersMethodupdate_diffusion_transformer
(self, diffusion_transformer_dropdown)
videox_fun/ui/wan_fun_ui.py:41
↓ 1 callersFunctionvideo_to_data_url
Convert video file to base64 data URL
VLM-MASK-REASONER/stage2_vlm_analysis.py:51
↓ 1 callersMethodwrite_video_frames
Write frames to a video file using lossless H.264
VLM-MASK-REASONER/edit_quadmask.py:271
Method__call__
(self, n_samples, generator=None, device=None)
videox_fun/utils/discrete_sampler.py:31
Method__call__
Given batch frames with shape `[B, C, T, H, W]` extracted from a list of videos and a list of prompts (optional) correspondingly, return the
videox_fun/reward/reward_fn.py:24
Method__call__
(self, batch_frames: torch.Tensor, batch_prompt: Optional[list[str]]=None)
videox_fun/reward/reward_fn.py:79
Method__call__
(self, batch_frames: torch.Tensor, batch_prompt: list[str])
videox_fun/reward/reward_fn.py:168
Method__call__
(self, batch_frames: torch.Tensor, batch_prompt: list[str])
videox_fun/reward/reward_fn.py:223
Method__call__
( self, batch_frames: torch.Tensor, batch_prompt: list[str], batch_condition:
videox_fun/reward/reward_fn.py:314
Method__call__
(self, *args, **kwargs)
videox_fun/reward/aesthetic_predictor_v2_5/siglip_v2_5.py:95
Method__call__
Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):
videox_fun/pipeline/pipeline_cogvideox_fun.py:593
Method__call__
Function invoked when calling the pipeline for generation. Args: Examples: Returns:
videox_fun/pipeline/pipeline_wan_fun.py:383
Method__call__
Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:740
Method__del__
Clean up video captures
VLM-MASK-REASONER/point_selector_gui.py:582
Method__getitem__
(self, idx)
videox_fun/data/dataset_image_video.py:790
Method__getitem__
(self, idx)
videox_fun/data/dataset_image_video.py:1028
Method__getitem__
(self, idx)
videox_fun/data/dataset_image_video_warped.py:815
Method__getitem__
(self, idx)
videox_fun/data/dataset_image_video_warped.py:1053
Method__getitem__
(self, idx)
videox_fun/data/dataset_video.py:136
Method__getitem__
(self, idx)
videox_fun/data/dataset_video.py:222
Method__getitem__
(self, idx)
videox_fun/data/dataset_image.py:51
Method__init__
(self)
data_generation/scripts/transfer_human_model.py:36
Method__init__
Initialize differentiable mesh deformer with enhanced joint functionality
data_generation/human_model/human_model.py:28
Method__init__
(self, model_type: str = "sam3")
VLM-MASK-REASONER/stage3a_generate_grey_masks_v2.py:74
Method__init__
(self, model_type: str = "sam3")
VLM-MASK-REASONER/stage3a_generate_grey_masks.py:48
Method__init__
(self, root)
VLM-MASK-REASONER/edit_quadmask.py:16
Method__init__
(self, root, objects_data: List[Dict])
VLM-MASK-REASONER/stage3b_trajectory_gui.py:57
Method__init__
(self, checkpoint_path: str, model_cfg: str = "sam2_hiera_l.yaml", device: str = "cuda")
VLM-MASK-REASONER/stage1_sam2_segmentation.py:45
Method__init__
(self, root, config_path=None)
VLM-MASK-REASONER/point_selector_gui.py:26
Method__init__
Initialize RAFT flow extractor. Args: device: Device to run RAFT on ('cuda' or 'cpu') model_weights: Optiona
videox_fun/utils/optical_flow_utils.py:46
Method__init__
(self, num_idx, uniform_sampling=False)
videox_fun/utils/discrete_sampler.py:6
Method__init__
( self, text_encoder: Union[List[T5EncoderModel], T5EncoderModel], unet, multi
videox_fun/utils/lora_utils.py:163
Method__init__
(self, p1, p2, angle1, angle2, **kw)
videox_fun/data/dataset_image_video.py:41
Method__init__
(self, sampler: Sampler, dataset: Dataset, batch_size: int,
videox_fun/data/dataset_image_video.py:288
Method__init__
( self, ann_path, data_root=None, video_sample_size=512, video_sample_stri
videox_fun/data/dataset_image_video.py:378
Method__init__
( self, ann_path, data_root=None, video_sample_size=512, video_sample_stri
videox_fun/data/dataset_image_video.py:842
Method__init__
(self, p1, p2, angle1, angle2, **kw)
videox_fun/data/dataset_image_video_warped.py:41
Method__init__
(self, sampler: Sampler, dataset: Dataset, batch_size: int,
videox_fun/data/dataset_image_video_warped.py:288
Method__init__
( self, ann_path, data_root=None, video_sample_size=512, video_sample_stri
videox_fun/data/dataset_image_video_warped.py:378
Method__init__
( self, ann_path, data_root=None, video_sample_size=512, video_sample_stri
videox_fun/data/dataset_image_video_warped.py:867
Method__init__
(self, data_source: Sized, replacement: bool = False, num_samples: Optional[int] = None, gene
videox_fun/data/bucket_sampler.py:65
Method__init__
( self, sampler: Sampler, dataset: Dataset, batch_size: int, train_fol
videox_fun/data/bucket_sampler.py:125
Method__init__
( self, sampler: Sampler, dataset: Dataset, batch_size: int, video_fol
videox_fun/data/bucket_sampler.py:199
Method__init__
(self, sampler: Sampler, dataset: Dataset, batch_size: int,
videox_fun/data/bucket_sampler.py:283
Method__init__
( self, csv_path, video_folder, sample_size=256, sample_stride=4, sample_n
videox_fun/data/dataset_video.py:81
Method__init__
( self, json_path, video_folder=None, sample_size=256, sample_stride=4, sample_n_frame
videox_fun/data/dataset_video.py:158
Method__init__
( self, json_path, video_folder=None, resolution=512,
videox_fun/data/dataset_image.py:13
Method__init__
Define your reward model and image transformations (optional) here.
videox_fun/reward/reward_fn.py:18
Method__init__
( self, encoder_path="openai/clip-vit-large-patch14", predictor_path=None, ver
videox_fun/reward/reward_fn.py:34
Method__init__
( self, model_path=None, version="v2.0", device="cpu", dtype=torch.flo
videox_fun/reward/reward_fn.py:102
Method__init__
( self, model_path="yuvalkirstain/PickScore_v1", device="cpu", dtype=torch.flo
videox_fun/reward/reward_fn.py:196
Method__init__
( self, model_path=None, device="cpu", dtype=torch.float16, max_reward
videox_fun/reward/reward_fn.py:259
Method__init__
(self, encoder_path="openai/clip-vit-large-patch14", predictor_path=None)
videox_fun/reward/improved_aesthetic_predictor.py:33
Method__init__
(self, config: SiglipVisionConfig, *args, **kwargs)
videox_fun/reward/aesthetic_predictor_v2_5/siglip_v2_5.py:48
Method__init__
(self, *args, **kwargs)
videox_fun/reward/aesthetic_predictor_v2_5/siglip_v2_5.py:92
Method__init__
(self, config: CLIPConfig)
videox_fun/reward/MPS/trainer/models/clip_model.py:22
Method__init__
(self, dim)
videox_fun/reward/MPS/trainer/models/cross_modeling.py:19
Method__init__
(self, dim)
videox_fun/reward/MPS/trainer/models/cross_modeling.py:44
Method__init__
(self, dim, dim_head=64, heads=8, ff_mult=4)
videox_fun/reward/MPS/trainer/models/cross_modeling.py:79
Method__init__
( self, dim, *, context_dim=None, dim_head=64, heads=12,
videox_fun/reward/MPS/trainer/models/cross_modeling.py:173
Method__init__
( self, dim=512, layer_num=4, dim_head=64, heads=8, ff_mult=4
videox_fun/reward/MPS/trainer/models/cross_modeling.py:262
Method__init__
( self, rank: int, world_size: int, Controller, GPU_memory_mode, scheduler_dict, model
videox_fun/api/api_multi_nodes.py:24
Method__init__
( self, world_size, Controller, GPU_memory_mode,
videox_fun/api/api_multi_nodes.py:157
Method__init__
( self, in_channels: int, out_channels: int, kernel_size: Union[int, Tuple[int
videox_fun/models/cogvideox_vae.py:83
Method__init__
( self, f_channels: int, zq_channels: int, groups: int = 32, )
videox_fun/models/cogvideox_vae.py:166
Method__init__
( self, in_channels: int, out_channels: int, kernel_size: int = 3, str
videox_fun/models/cogvideox_vae.py:220
Method__init__
( self, in_channels: int, out_channels: Optional[int] = None, dropout: float =
videox_fun/models/cogvideox_vae.py:303
Method__init__
( self, in_channels: int, out_channels: int, temb_channels: int, dropo
videox_fun/models/cogvideox_vae.py:438
Method__init__
( self, in_channels: int, temb_channels: int, dropout: float = 0.0, nu
videox_fun/models/cogvideox_vae.py:554
Method__init__
( self, in_channels: int = 3, out_channels: int = 16, down_block_types: Tuple[
videox_fun/models/cogvideox_vae.py:767
Method__init__
( self, in_channels: int = 16, out_channels: int = 3, up_block_types: Tuple[st
videox_fun/models/cogvideox_vae.py:926
Method__init__
( self, in_channels: int = 3, out_channels: int = 3, down_block_types: Tuple[s
videox_fun/models/cogvideox_vae.py:1105
Method__init__
( self, patch_size: int = 2, patch_size_t: Optional[int] = None, in_channels:
videox_fun/models/cogvideox_transformer3d.py:49
Method__init__
( self, num_attention_heads: int = 30, attention_head_dim: int = 64, in_channe
videox_fun/models/cogvideox_transformer3d.py:354
Method__init__
( self, coefficients: list[float], num_steps: int, rel_l1_thresh: float = 0.0,
videox_fun/models/cache_utils.py:27
Method__init__
( self, tokenizer: T5Tokenizer, text_encoder: T5EncoderModel, vae: Autoencoder
videox_fun/pipeline/pipeline_cogvideox_fun.py:267
Method__init__
( self, tokenizer: AutoTokenizer, text_encoder: WanT5EncoderModel, vae: Autoen
videox_fun/pipeline/pipeline_wan_fun.py:121
Method__init__
( self, tokenizer: T5Tokenizer, text_encoder: T5EncoderModel, vae: Autoencoder
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:319
Method__iter__
(self)
videox_fun/data/dataset_image_video.py:308
Method__iter__
(self)
videox_fun/data/dataset_image_video_warped.py:308
Method__iter__
(self)
videox_fun/data/bucket_sampler.py:86
Method__iter__
(self)
videox_fun/data/bucket_sampler.py:154
Method__iter__
(self)
videox_fun/data/bucket_sampler.py:230
Method__iter__
(self)
videox_fun/data/bucket_sampler.py:311
Method__len__
(self)
videox_fun/data/dataset_image_video.py:787
Method__len__
(self)
videox_fun/data/dataset_image_video.py:1025
Method__len__
(self)
videox_fun/data/dataset_image_video_warped.py:812
Method__len__
(self)
videox_fun/data/dataset_image_video_warped.py:1050
Method__len__
(self)
videox_fun/data/bucket_sampler.py:111
Method__len__
(self)
videox_fun/data/dataset_video.py:133
Method__len__
(self)
videox_fun/data/dataset_video.py:219
Method__len__
(self)
videox_fun/data/dataset_image.py:48
Function_get_gaussian_kernel
Create a 2D Gaussian kernel for spatial smoothing.
videox_fun/utils/optical_flow_utils.py:418
Function_infer_forward_api
( datas: dict, )
videox_fun/api/api.py:110
Function_multi_nodes_infer_forward_api
( datas: dict, )
videox_fun/api/api_multi_nodes.py:202
Method_sample
(_latents, _inpaint_latents)
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:1123
Method_set_gradient_checkpointing
(self, module, value=False)
videox_fun/models/cogvideox_transformer3d.py:460
Function_update_diffusion_transformer_api
( datas: dict, )
videox_fun/api/api.py:43
Function_update_edition_api
( datas: dict, )
videox_fun/api/api.py:25
Functionanimate_camera
Animate camera with different motion types. Args: camera_obj: Blender camera object initial_location: Initial camera locatio
data_generation/blender_utils.py:427
← previousnext →401–500 of 673, ranked by callers