MCPcopy Create free account

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

Functions673 in github.com/Netflix/void-model

↓ 1 callersFunctionload_character_fbx
Load character FBX file (Remy or Sophie). Returns armature, character meshes, and scene objects dict. The scene objects from the FBX are at t
data_generation/render_paired_videos_blender_quadmask.py:1183
↓ 1 callersFunctionload_config
Load existing physics configuration.
data_generation/physics_review_ui.py:34
↓ 1 callersMethodload_config_direct
Load config from path (for command line usage)
VLM-MASK-REASONER/point_selector_gui.py:164
↓ 1 callersMethodload_existing_points
Load existing points from output file if it exists
VLM-MASK-REASONER/point_selector_gui.py:275
↓ 1 callersFunctionload_metadata
Load sequence metadata.
data_generation/physics_review_ui.py:23
↓ 1 callersFunctionload_object_model
Load object mesh from model directory. Args: object_name: Name of the object object_model_dir: Path to object models directo
data_generation/blender_utils.py:186
↓ 1 callersFunctionload_physics_config
Load physics configuration for a specific sequence. Returns: dict: Configuration with 'static_objects' and 'physics_objects' lists,
data_generation/render_paired_videos_blender_quadmask.py:86
↓ 1 callersFunctionload_pipeline
(config)
inference/cogvideox_fun/predict_v2v.py:41
↓ 1 callersFunctionload_progress
Load conversion progress.
data_generation/convert_all_scenarios_for_characters.py:41
↓ 1 callersMethodload_videos
Load RGB and mask videos into memory
VLM-MASK-REASONER/edit_quadmask.py:215
↓ 1 callersFunctionmain
()
data_generation/generate_review_frames.py:201
↓ 1 callersFunctionmain
()
data_generation/convert_all_scenarios_for_characters.py:143
↓ 1 callersFunctionmain
()
data_generation/generate_review_frames_direct.py:144
↓ 1 callersFunctionmain
()
data_generation/convert_trimask_to_quadmask.py:244
↓ 1 callersFunctionmain
()
data_generation/generate_physics_config.py:13
↓ 1 callersFunctionmain
()
data_generation/render_paired_videos_blender_quadmask.py:2180
↓ 1 callersFunctionmain
()
data_generation/convert_masks_to_grid_hybrid.py:311
↓ 1 callersFunctionmain
()
data_generation/physics_review_ui.py:48
↓ 1 callersFunctionmain
()
data_generation/kubric_variable_objects.py:609
↓ 1 callersFunctionmain
()
inference/cogvideox_fun/inference_with_pass1_warped_noise.py:218
↓ 1 callersFunctionmain
()
scripts/cogvideox_fun/train.py:728
↓ 1 callersFunctionmain
()
scripts/cogvideox_fun/train_warped_noise.py:746
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/stage2_vlm_analysis_cf.py:1014
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/stage3a_generate_grey_masks_v2.py:513
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/stage3a_generate_grey_masks.py:368
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/stage2_vlm_analysis.py:1012
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/stage4_combine_masks.py:225
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/stage3b_trajectory_gui.py:376
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/test_gemini_video.py:47
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/stage1_sam2_segmentation.py:395
↓ 1 callersFunctionmain
()
VLM-MASK-REASONER/point_selector_gui.py:589
↓ 1 callersFunctionmask_to_fixed_bbox
(video_mask)
videox_fun/utils/utils.py:549
↓ 1 callersMethodnext_frame
Go to next frame
VLM-MASK-REASONER/edit_quadmask.py:794
↓ 1 callersMethodopen_videos
Open all videos for frame navigation
VLM-MASK-REASONER/point_selector_gui.py:238
↓ 1 callersFunctionparse_args
Parse command line arguments after '--' separator.
data_generation/render_paired_videos_blender_quadmask.py:105
↓ 1 callersFunctionparse_args
()
scripts/cogvideox_fun/train.py:286
↓ 1 callersFunctionparse_args
()
scripts/cogvideox_fun/train_warped_noise.py:287
↓ 1 callersFunctionparse_vlm_response
Parse VLM JSON response
VLM-MASK-REASONER/stage2_vlm_analysis_cf.py:642
↓ 1 callersFunctionparse_vlm_response
Parse VLM JSON response
VLM-MASK-REASONER/stage2_vlm_analysis.py:638
↓ 1 callersFunctionpoints_to_grid_cells
Convert trajectory points to grid cells
VLM-MASK-REASONER/stage3b_trajectory_gui.py:39
↓ 1 callersFunctionprecalculate_safetensors_hashes
Precalculate the model hashes needed by sd-webui-additional-networks to save time on indexing the model later.
videox_fun/utils/lora_utils.py:141
↓ 1 callersFunctionprecompute_motion_dataset
Precompute motion RGB videos for an entire dataset. IMPORTANT: Extract flow from GROUND TRUTH videos (person removed, correct physics).
videox_fun/utils/optical_flow_utils.py:626
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
videox_fun/pipeline/pipeline_cogvideox_fun.py:449
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
videox_fun/pipeline/pipeline_wan_fun.py:296
↓ 1 callersMethodprepare_extra_step_kwargs
(self, generator, eta)
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:586
↓ 1 callersMethodprepare_latents
( self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents
videox_fun/pipeline/pipeline_cogvideox_fun.py:412
↓ 1 callersMethodprepare_latents
( self, batch_size, num_channels_latents, num_frames, height, width, dtype, device, generator, latents
videox_fun/pipeline/pipeline_wan_fun.py:261
↓ 1 callersMethodprepare_latents
( self, batch_size, num_channels_latents, height, width, vide
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:470
↓ 1 callersMethodprepare_mask_latents
( self, mask, masked_image, batch_size, height, width, dtype, device, generator, do_classifier_free_gu
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:538
↓ 1 callersMethodprev_frame
Go to previous frame
VLM-MASK-REASONER/edit_quadmask.py:788
↓ 1 callersMethodprev_video
Go to previous video
VLM-MASK-REASONER/point_selector_gui.py:496
↓ 1 callersFunctionprint_texture_summary
Print summary of texture assignments.
data_generation/object_texture_mapping.py:377
↓ 1 callersFunctionprocess_config
Process all videos in config
VLM-MASK-REASONER/stage2_vlm_analysis_cf.py:932
↓ 1 callersFunctionprocess_config
Process all videos in config
VLM-MASK-REASONER/stage2_vlm_analysis.py:937
↓ 1 callersFunctionprocess_config
Process all videos in config
VLM-MASK-REASONER/stage4_combine_masks.py:149
↓ 1 callersFunctionprocess_config
Process all videos in config
VLM-MASK-REASONER/stage1_sam2_segmentation.py:249
↓ 1 callersFunctionprocess_sequence
Process a single sequence to create paired videos.
data_generation/render_paired_videos_blender_quadmask.py:1286
↓ 1 callersFunctionprocess_video
Process a single video with VLM analysis
VLM-MASK-REASONER/stage2_vlm_analysis_cf.py:749
↓ 1 callersFunctionprocess_video
Process a single video with VLM analysis
VLM-MASK-REASONER/stage2_vlm_analysis.py:745
↓ 1 callersFunctionprocess_video
Combine black and grey mask videos into trimask/quadmask
VLM-MASK-REASONER/stage4_combine_masks.py:58
↓ 1 callersFunctionprocess_video_grey_masks
Generate grey masks for a single video
VLM-MASK-REASONER/stage3a_generate_grey_masks_v2.py:338
↓ 1 callersFunctionprocess_video_grey_masks
Generate grey masks for a single video
VLM-MASK-REASONER/stage3a_generate_grey_masks.py:195
↓ 1 callersFunctionquantize_to_trimask
Quantize mask to tri-mask values (0, 127, 255).
data_generation/convert_trimask_to_quadmask.py:27
↓ 1 callersFunctionrandom_shift
(x, y, scale_range = [0.2, 0.7], trans_perturb_range=[-0.2, 0.2])
videox_fun/data/dataset_image_video.py:121
↓ 1 callersFunctionrandom_shift
(x, y, scale_range = [0.2, 0.7], trans_perturb_range=[-0.2, 0.2])
videox_fun/data/dataset_image_video_warped.py:121
↓ 1 callersMethodredo
Redo last undone edit
VLM-MASK-REASONER/edit_quadmask.py:737
↓ 1 callersFunctionrender_first_frame
Render first frame directly using bpy.
data_generation/generate_review_frames_direct.py:55
↓ 1 callersFunctionrender_first_frame_simple
Render first frame using a simple Blender script.
data_generation/generate_review_frames.py:45
↓ 1 callersFunctionreplace_parameters_by_name
(module, name_keywords, device)
videox_fun/utils/fp8_optimization.py:17
↓ 1 callersFunctionretrieve_timesteps
Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs
videox_fun/pipeline/pipeline_cogvideox_fun.py:161
↓ 1 callersFunctionrgb_to_hsv_torch
Convert RGB to HSV color space using PyTorch operations. Args: rgb: RGB tensor [..., 3, H, W] with values in [0, 1] Returns:
videox_fun/utils/optical_flow_utils.py:524
↓ 1 callersFunctionrotate_half
(x)
videox_fun/reward/MPS/trainer/models/cross_modeling.py:55
↓ 1 callersFunctionrotmat_yup_to_blender
Convert 3x3 rotation matrix from Y-up to Blender coordinate system.
data_generation/render_paired_videos_blender_quadmask.py:63
↓ 1 callersFunctionrun_inference
(config, pipeline, vae, generator, input_video_name, keep_fg_ids=[-1])
inference/cogvideox_fun/predict_v2v.py:173
↓ 1 callersFunctionsample_frames
Sample n evenly-spaced frames from the video, return as base64 data URLs.
VLM-MASK-REASONER/test_gemini_video.py:27
↓ 1 callersFunctionsave_inout_row
(input_video, input_mask, output_video, video_path, fps=16, visualize_masked_video=False, visualize_error=True
videox_fun/utils/utils.py:92
↓ 1 callersMethodschedule_brush_repeat
Schedule continuous brush application while mouse is held down
VLM-MASK-REASONER/edit_quadmask.py:615
↓ 1 callersMethodsegment
Segment object using text prompt
VLM-MASK-REASONER/stage3a_generate_grey_masks.py:66
↓ 1 callersFunctionsegment_object_all_frames
Segment object through all frames. Args: video_path: Path to video obj_noun: Object to segment segmenter: Segmentati
VLM-MASK-REASONER/stage3a_generate_grey_masks_v2.py:268
↓ 1 callersFunctionselect_character
Select which character to use for this sequence. Args: sequence_name: Name of the sequence (for consistent random selection)
data_generation/render_paired_videos_blender_quadmask.py:1262
↓ 1 callersFunctionselect_random_floor_texture
Select a random floor texture from available textures. Searches both original textures and new Blender textures for maximum variety. Args:
data_generation/render_paired_videos_blender_quadmask.py:210
↓ 1 callersFunctionselect_random_wall_texture
Select a random wall texture from available textures. Searches both original textures and new Blender textures for maximum variety.
data_generation/render_paired_videos_blender_quadmask.py:355
↓ 1 callersFunctionsetup_camera
Setup camera.
data_generation/render_paired_videos_blender_quadmask.py:827
↓ 1 callersFunctionsetup_lighting
Setup scene lighting with optional randomization. Args: y_up: Whether using Y-up coordinate system seed: Random seed for lighting
data_generation/render_paired_videos_blender_quadmask.py:611
↓ 1 callersFunctionsetup_scene
Setup basic Blender scene for rendering.
data_generation/render_paired_videos_blender_quadmask.py:176
↓ 1 callersMethodsetup_ui
Setup the GUI layout
VLM-MASK-REASONER/edit_quadmask.py:55
↓ 1 callersMethodsetup_ui
Setup GUI layout
VLM-MASK-REASONER/stage3b_trajectory_gui.py:80
↓ 1 callersMethodsetup_ui
Setup the GUI layout
VLM-MASK-REASONER/point_selector_gui.py:52
↓ 1 callersFunctionshould_use_texture
Determine if an object should use texture or solid color. Args: obj_name: Name of the object Returns: bool: True if obj
data_generation/object_texture_mapping.py:351
↓ 1 callersMethodskip_object
Skip current object without saving trajectory
VLM-MASK-REASONER/stage3b_trajectory_gui.py:270
↓ 1 callersFunctionsubsample_sequence
Subsample sequence data to target number of frames. Args: data: Dictionary with 'armature' and 'objects' target_frames: Targ
data_generation/blender_utils.py:233
↓ 1 callersMethodtensor_to_pose_params
Convert pose tensor to pose parameters Args: pose_tensor: Tensor [batch_size, num_bones, 4, 4] Returns:
data_generation/human_model/human_model.py:224
↓ 1 callersMethodtiled_decode
r""" Decode a batch of images using a tiled decoder. Args: z (`torch.Tensor`): Input batch of latent vectors.
videox_fun/models/cogvideox_vae.py:1508
↓ 1 callersMethodtiled_encode
r"""Encode a batch of images using a tiled encoder. When this option is enabled, the VAE will split the input tensor into tiles to compute en
videox_fun/models/cogvideox_vae.py:1434
↓ 1 callersMethodtoggle_grid
Toggle a grid cell between 127 and 255, handling 63 overlaps
VLM-MASK-REASONER/edit_quadmask.py:446
↓ 1 callersMethodtoggle_grid_black
Toggle black mask in a grid cell
VLM-MASK-REASONER/edit_quadmask.py:484
↓ 1 callersMethodtransfer_animation
Transfers animation from the source to the target armature over a specified frame range. Args: source_a
data_generation/scripts/transfer_human_model.py:39
↓ 1 callersFunctiontransfer_animation_between_armatures
A helper function to easily transfer animation between two armatures in the scene. Args: source_name: The name of the source armature obj
data_generation/scripts/transfer_human_model.py:114
↓ 1 callersMethodundo
Undo last edit
VLM-MASK-REASONER/edit_quadmask.py:718
↓ 1 callersMethodundo_last_point
Remove last point from current frame
VLM-MASK-REASONER/point_selector_gui.py:434
← previousnext →301–400 of 673, ranked by callers