MCPcopy Create free account

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

Functions673 in github.com/Netflix/void-model

⨍ Functions 673◇ Types & classes 74↳ Endpoints 4
↓ 46 callersMethodfrom_pretrained
(cls, pretrained_model_path, subfolder=None, **vae_additional_kwargs)
videox_fun/models/cogvideox_vae.py:1651
↓ 16 callersMethodupdate_display
Update both canvas displays (or just mask in fast mode)
VLM-MASK-REASONER/edit_quadmask.py:300
↓ 11 callersFunctionsave_videos_grid
(videos: torch.Tensor, path: str, rescale=False, n_rows=6, fps=12, imageio_backend=True, color_transfer_post_p
videox_fun/utils/utils.py:65
↓ 9 callersMethod__init__
( self, in_channels: int, out_channels: int, temb_channels: int, dropo
videox_fun/models/cogvideox_vae.py:652
↓ 9 callersMethoddecode
Decode a batch of images. Args: z (`torch.Tensor`): Input batch of latent vectors. return_dict (`bool`, *opt
videox_fun/models/cogvideox_vae.py:1394
↓ 9 callersFunctionresize_frame
(frame, target_short_side)
videox_fun/data/dataset_image_video.py:360
↓ 9 callersFunctionresize_frame
(frame, target_short_side)
videox_fun/data/dataset_image_video_warped.py:360
↓ 9 callersMethodsave_state
Save current state for undo
VLM-MASK-REASONER/edit_quadmask.py:701
↓ 9 callersFunctionunwrap_model
(model)
scripts/cogvideox_fun/train.py:1388
↓ 9 callersFunctionunwrap_model
(model)
scripts/cogvideox_fun/train_warped_noise.py:1433
↓ 8 callersFunctionget_image_to_video_latent
(validation_image_start, validation_image_end, video_length, sample_size)
videox_fun/utils/utils.py:117
↓ 8 callersMethodsave
(self, path)
videox_fun/reward/MPS/trainer/models/clip_model.py:153
↓ 7 callersMethodfrom_pretrained
( self, pretrained_model_name_or_path: str | PathLike = "google/siglip-so400m-patch14-
videox_fun/reward/aesthetic_predictor_v2_5/siglip_v2_5.py:99
↓ 6 callersFunctioncreate_cfg_and_seedbox
(gradio_version_is_above_4)
videox_fun/ui/ui.py:268
↓ 6 callersFunctioncreate_generation_method
(source_method_options, prompt_textbox, support_end_image=True)
videox_fun/ui/ui.py:201
↓ 6 callersFunctioncreate_generation_methods_and_video_length
( generation_method_options, default_video_length, maximum_video_length )
videox_fun/ui/ui.py:183
↓ 6 callersFunctioncreate_prompts
( prompt="A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest
videox_fun/ui/ui.py:138
↓ 6 callersFunctioncreate_samplers
(controller, maximum_step=100)
videox_fun/ui/ui.py:152
↓ 6 callersFunctioncreate_ui_outputs
()
videox_fun/ui/ui.py:281
↓ 6 callersMethoddisplay_frame
Display current frame with points
VLM-MASK-REASONER/point_selector_gui.py:364
↓ 6 callersMethodencode
Encode a batch of images into latents. Args: x (`torch.Tensor`): Input batch of images. return_dict (`bool`,
videox_fun/models/cogvideox_vae.py:1312
↓ 6 callersFunctionget_3d_rotary_pos_embed
RoPE for video tokens with 3D structure. Args: embed_dim: (`int`): The embedding dimension size, corresponding to hidden_size_he
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:49
↓ 6 callersFunctionsave_url_image
(url)
videox_fun/api/api.py:102
↓ 5 callersFunctionVideoReader_contextmanager
(*args, **kwargs)
videox_fun/data/dataset_image_video.py:329
↓ 5 callersFunctionVideoReader_contextmanager
(*args, **kwargs)
videox_fun/data/dataset_image_video_warped.py:329
↓ 5 callersMethod__init__
(self, fn)
videox_fun/reward/MPS/trainer/models/cross_modeling.py:31
↓ 5 callersFunctioncleanup_scene
Clean up Blender and PyBullet to prevent memory leaks
data_generation/kubric_variable_objects.py:46
↓ 5 callersMethoddisplay_current_video
Display current video frame
VLM-MASK-REASONER/point_selector_gui.py:321
↓ 5 callersFunctionframes_to_video
Convert image sequence to video using ffmpeg. Args: frames_dir: Directory containing frame_%04d.png files output_path: Output vid
data_generation/render_paired_videos_blender_quadmask.py:977
↓ 5 callersFunctionsave_base64_video
(base64_string)
videox_fun/api/api.py:68
↓ 5 callersMethodsave_current_points
Save current video's points to storage
VLM-MASK-REASONER/point_selector_gui.py:520
↓ 5 callersMethodupdate_frame_display
Update frame label and display
VLM-MASK-REASONER/point_selector_gui.py:475
↓ 5 callersMethodupdate_frames_display
Update display showing which frames have points
VLM-MASK-REASONER/point_selector_gui.py:351
↓ 4 callersFunction_batch_encode_vae
(pixel_values)
scripts/cogvideox_fun/train.py:1608
↓ 4 callersFunction_batch_encode_vae
(pixel_values)
scripts/cogvideox_fun/train_warped_noise.py:1668
↓ 4 callersFunctioncreate_fake_finetune_models_checkpoints
(visible)
videox_fun/ui/ui.py:111
↓ 4 callersFunctioncreate_fake_model_checkpoints
(model_name, visible)
videox_fun/ui/ui.py:67
↓ 4 callersFunctioncreate_height_width
(default_height, default_width, maximum_height, maximum_width)
videox_fun/ui/ui.py:159
↓ 4 callersMethoddecode_latents
(self, latents: torch.Tensor)
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:575
↓ 4 callersMethoddisplay_frame
Display frame with trajectory
VLM-MASK-REASONER/stage3b_trajectory_gui.py:191
↓ 4 callersFunctionencode_sequence
(pattern_glob: str, out_mp4: Path, fps: int, lossless: bool = False)
data_generation/kubric_variable_objects.py:139
↓ 4 callersFunctionget_random_mask
(shape, mask_type_probs=[0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.8])
videox_fun/data/dataset_image_video.py:177
↓ 4 callersFunctionget_video_to_video_latent
(input_video_path, video_length, sample_size, fps=None, validation_video_mask=None, ref_image=None)
videox_fun/utils/utils.py:213
↓ 4 callersFunctionimage_to_data_url
Convert image file to base64 data URL
VLM-MASK-REASONER/stage2_vlm_analysis_cf.py:35
↓ 4 callersFunctionimage_to_data_url
Convert image file to base64 data URL
VLM-MASK-REASONER/stage2_vlm_analysis.py:34
↓ 4 callersMethodnext_frame
Go to next frame
VLM-MASK-REASONER/point_selector_gui.py:463
↓ 4 callersMethodprev_frame
Go to previous frame
VLM-MASK-REASONER/point_selector_gui.py:457
↓ 4 callersFunctionsave_url_video
(url)
videox_fun/api/api.py:96
↓ 4 callersFunctiontemporal_padding
(video, min_length=85, max_length=197, dim=2)
videox_fun/utils/utils.py:282
↓ 4 callersFunctionunmerge_lora
Unmerge state_dict in LoRANetwork from the pipeline in diffusers.
videox_fun/utils/lora_utils.py:446
↓ 3 callersFunction_read_video_from_dir
(video_dir)
videox_fun/data/dataset_image_video.py:343
↓ 3 callersFunction_read_video_from_dir
(video_dir)
videox_fun/data/dataset_image_video_warped.py:343
↓ 3 callersFunctionadd_noise_to_reference_video
(image, ratio=None)
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:259
↓ 3 callersMethodapply_brush
Apply brush to add/erase black mask (vectorized for speed)
VLM-MASK-REASONER/edit_quadmask.py:522
↓ 3 callersFunctionapply_pbr_texture
Apply PBR textures to an object. Args: obj: Blender object to apply texture to texture_path: Path to texture directory sc
data_generation/render_paired_videos_blender_quadmask.py:530
↓ 3 callersFunctionclean_scene
Clean the scene by reading the home file. Returns: None
data_generation/scripts/blender_helper.py:5
↓ 3 callersFunctionconvert_weight_dtype_wrapper
(module, origin_dtype)
videox_fun/utils/fp8_optimization.py:45
↓ 3 callersMethodenable_multi_gpus_inference
(self,)
videox_fun/models/cogvideox_transformer3d.py:463
↓ 3 callersFunctionexists
(val)
videox_fun/reward/MPS/trainer/models/cross_modeling.py:8
↓ 3 callersFunctionextract_frames
Extract all frames from a video using ffmpeg.
data_generation/convert_trimask_to_quadmask.py:86
↓ 3 callersMethodgenerate
(self, data)
videox_fun/api/api_multi_nodes.py:191
↓ 3 callersFunctionget_armature
Get the armature object from the scene. Args: objects: The objects to search for the armature. If None, all objects in the scene are
data_generation/scripts/blender_helper.py:58
↓ 3 callersMethodget_image_features
(self, *args, **kwargs)
videox_fun/reward/MPS/trainer/models/clip_model.py:113
↓ 3 callersFunctionget_image_size_without_loading
(path)
videox_fun/data/bucket_sampler.py:46
↓ 3 callersFunctionget_random_mask
(shape, mask_type_probs=[0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.8])
videox_fun/data/dataset_image_video_warped.py:177
↓ 3 callersFunctionget_resize_crop_region_for_grid
(src, tgt_width, tgt_height)
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:144
↓ 3 callersMethodget_text_features
(self, *args, **kwargs)
videox_fun/reward/MPS/trainer/models/clip_model.py:110
↓ 3 callersMethodload_current_object
Load current object for trajectory drawing
VLM-MASK-REASONER/stage3b_trajectory_gui.py:128
↓ 3 callersFunctionload_humoto_fbx
Load FBX file and return status. Args: fbx_path: The path to the FBX file to load. Returns: True if the FBX file
data_generation/scripts/blender_helper.py:13
↓ 3 callersFunctionmerge_lora
(pipeline, lora_path, multiplier, device='cpu', dtype=torch.float32, state_dict=None, transformer_only=False)
videox_fun/utils/lora_utils.py:368
↓ 3 callersFunctionquat_yup_to_blender
Convert quaternion from Y-up to Blender coordinate system. Args: qwxyz: Quaternion in [w, x, y, z] format Returns: mathutils
data_generation/render_paired_videos_blender_quadmask.py:69
↓ 3 callersFunctionrender_video
Render animation to video.
data_generation/render_paired_videos_blender_quadmask.py:951
↓ 3 callersFunctionrun_blender_script
Run a Blender Python script with arguments.
data_generation/convert_all_scenarios_for_characters.py:55
↓ 3 callersFunctionsave_base64_image
(base64_string)
videox_fun/api/api.py:82
↓ 3 callersMethodset_attn_processor
r""" Sets the attention processor to use to compute attention. Parameters: processor (`dict` of `AttentionProcessor` or o
videox_fun/models/cogvideox_transformer3d.py:494
↓ 2 callersMethod__init__
(self, config: SiglipVisionConfig)
videox_fun/reward/aesthetic_predictor_v2_5/siglip_v2_5.py:27
↓ 2 callersMethod__init__
( self, dim: int, num_attention_heads: int, attention_head_dim: int, t
videox_fun/models/cogvideox_transformer3d.py:213
↓ 2 callersFunction_create_special_list
(length)
scripts/cogvideox_fun/train.py:89
↓ 2 callersFunction_create_special_list
(length)
scripts/cogvideox_fun/train_warped_noise.py:90
↓ 2 callersMethod_decode
(self, z: torch.Tensor, return_dict: bool = True)
videox_fun/models/cogvideox_vae.py:1339
↓ 2 callersMethod_encode
(self, x: torch.Tensor)
videox_fun/models/cogvideox_vae.py:1285
↓ 2 callersMethod_get_t5_prompt_embeds
( self, prompt: Union[str, List[str]] = None, num_videos_per_prompt: int = 1,
videox_fun/pipeline/pipeline_cogvideox_fun.py:289
↓ 2 callersMethod_get_t5_prompt_embeds
( self, prompt: Union[str, List[str]] = None, num_videos_per_prompt: int = 1,
videox_fun/pipeline/pipeline_wan_fun.py:136
↓ 2 callersMethod_get_t5_prompt_embeds
( self, prompt: Union[str, List[str]] = None, num_videos_per_prompt: int = 1,
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:347
↓ 2 callersFunction_run_inference
()
inference/cogvideox_fun/predict_v2v.py:292
↓ 2 callersMethod_set_first_frame
(self)
videox_fun/models/cogvideox_vae.py:1264
↓ 2 callersMethod_set_gradient_checkpointing
(self, module, value=False)
videox_fun/models/cogvideox_vae.py:1203
↓ 2 callersMethod_set_rest_frame
(self)
videox_fun/models/cogvideox_vae.py:1270
↓ 2 callersMethod_tokenize
(self, caption)
videox_fun/reward/reward_fn.py:303
↓ 2 callersFunctionapply_camera_motion
Apply camera motion animation based on motion type. Args: camera: Kubric camera object motion_type: One of ['static', 'zoom_in',
data_generation/kubric_variable_objects.py:58
↓ 2 callersMethodblend_h
(self, a: torch.Tensor, b: torch.Tensor, blend_extent: int)
videox_fun/models/cogvideox_vae.py:1426
↓ 2 callersMethodblend_v
(self, a: torch.Tensor, b: torch.Tensor, blend_extent: int)
videox_fun/models/cogvideox_vae.py:1418
↓ 2 callersFunctioncalculate_square_grid
Calculate grid dimensions matching stage3a logic
VLM-MASK-REASONER/stage2_vlm_analysis_cf.py:59
↓ 2 callersFunctioncalculate_square_grid
Calculate grid dimensions matching stage3a logic
VLM-MASK-REASONER/stage2_vlm_analysis.py:58
↓ 2 callersFunctioncall_vlm_with_images_and_video
Call VLM with sampled frame images. The CF AI Gateway OpenAI-compat endpoint does not support video/mp4 base64 data URLs, so we rely solely o
VLM-MASK-REASONER/stage2_vlm_analysis_cf.py:608
↓ 2 callersFunctioncall_vlm_with_images_and_video
Call VLM with multiple images and video
VLM-MASK-REASONER/stage2_vlm_analysis.py:607
↓ 2 callersFunctionccw_sort
(p)
videox_fun/data/dataset_image_video.py:72
↓ 2 callersFunctionccw_sort
(p)
videox_fun/data/dataset_image_video_warped.py:72
↓ 2 callersFunctioncombine_time_height_width
(freqs_t, freqs_h, freqs_w)
videox_fun/pipeline/pipeline_cogvideox_fun.py:108
↓ 2 callersFunctioncombine_time_height_width
(freqs_t, freqs_h, freqs_w)
videox_fun/pipeline/pipeline_cogvideox_fun_inpaint.py:110
next →1–100 of 673, ranked by callers