MCPcopy Create free account

hub / github.com/character-ai/Ovi / functions

Functions478 in github.com/character-ai/Ovi

Methodforward
Forward pass of the function. Applies the function to the input elementwise. Snake ∶= x + 1/a * sin^2 (xa)
ovi/modules/mmaudio/ext/bigvgan_v2/activations.py:51
Methodforward
Forward pass of the function. Applies the function to the input elementwise. SnakeBeta ∶= x + 1/b * sin^2 (xa)
ovi/modules/mmaudio/ext/bigvgan_v2/activations.py:113
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/resample.py:26
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/resample.py:50
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/filter.py:94
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/act.py:27
Methodforward
(ctx, inputs, up_ftr, down_ftr, alpha, beta)
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/activation1d.py:22
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/models.py:95
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/models.py:156
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/models.py:223
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/bigvgan.py:25
Methodforward
Forward pass of the function. Applies the function to the input elementwise. Snake ∶= x + 1/a * sin^2 (xa)
ovi/modules/mmaudio/ext/bigvgan/activations.py:48
Methodforward
Forward pass of the function. Applies the function to the input elementwise. SnakeBeta ∶= x + 1/b * sin^2 (xa)
ovi/modules/mmaudio/ext/bigvgan/activations.py:107
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/resample.py:25
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/resample.py:46
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/filter.py:86
Methodforward
(self, x)
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/act.py:23
Methodforward
( ctx: Any, group: dist.ProcessGroup, input: Tensor, scatter_idx: int,
ovi/distributed_comms/communications.py:107
Methodforward
(ctx, input_, process_group, scatter_dim, gather_dim)
ovi/distributed_comms/communications.py:168
Methodforward
(ctx, input_, dim)
ovi/distributed_comms/communications.py:211
Functiongenerate_image
(text_prompt, image_seed, image_height, image_width)
gradio_app.py:109
Functiongenerate_video
( text_prompt, image, video_frame_height, video_frame_width, video_seed, solver_name,
gradio_app.py:64
Functionget_device
Get current rank device.
ovi/distributed_comms/util.py:28
Methodget_last_layer
(self)
ovi/modules/mmaudio/ext/autoencoder/vae.py:159
Functionget_sequence_parallel_group
Get the sequence parallel group the caller rank belongs to.
ovi/distributed_comms/util.py:34
Methodinit_weight
(self, conv)
ovi/modules/vae.py:162
Methodinit_weight
(self, conv)
ovi/modules/vae2_2.py:171
Methodinit_weight2
(self, conv)
ovi/modules/vae.py:174
Methodinit_weight2
(self, conv)
ovi/modules/vae2_2.py:182
Functioninit_weights
(m)
ovi/modules/t5.py:27
Functioninit_weights
(m, mean=0.0, std=0.01)
ovi/modules/mmaudio/ext/bigvgan_v2/utils.py:10
Functioninit_weights
(m, mean=0.0, std=0.01)
ovi/modules/mmaudio/ext/bigvgan/utils.py:10
Functioninitialize_sequence_parallel_group_custom
(process_group)
ovi/distributed_comms/parallel_states.py:63
Functioninitialize_sequence_parallelism
(sequence_parallel_size)
ovi/distributed_comms/util.py:38
Methodkl
(self, other=None)
ovi/modules/mmaudio/ext/autoencoder/distributions.py:26
Functionload
()
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/load.py:17
Functionload_checkpoint
(filepath, device)
ovi/modules/mmaudio/ext/bigvgan_v2/utils.py:26
Functionload_checkpoint
(filepath, device)
ovi/modules/mmaudio/ext/bigvgan/utils.py:26
Methodload_weights
(self, src_dict)
ovi/modules/mmaudio/ext/autoencoder/vae.py:152
Functionmp_cat
(a, b, dim=1, t=0.5)
ovi/modules/mmaudio/ext/autoencoder/edm2_utils.py:128
Functionnew_encode_text
(self, text, normalize: bool = False)
ovi/modules/mmaudio/features_utils.py:19
Methodnll
(self, sample, dims=[1, 2, 3])
ovi/modules/mmaudio/ext/autoencoder/distributions.py:37
Methodparam_groups
(self)
ovi/modules/clip.py:421
Functionpatch_clip
(clip_model)
ovi/modules/mmaudio/features_utils.py:16
Functionpreprocess_audio_tensor
Preprocess audio data into standardized tensor format.
ovi/utils/processing_utils.py:93
Functionprocess_vision_info
( conversations: list[dict] | list[list[dict]], )
ovi/utils/qwen_vl_utils.py:344
Methodremove_weight_norm
(self)
ovi/modules/mmaudio/ext/autoencoder/edm2_utils.py:160
Methodremove_weight_norm
(self)
ovi/modules/mmaudio/ext/bigvgan_v2/bigvgan.py:123
Methodremove_weight_norm
(self)
ovi/modules/mmaudio/ext/bigvgan_v2/bigvgan.py:204
Methodremove_weight_norm
(self)
ovi/modules/mmaudio/ext/bigvgan/models.py:164
Methodremove_weight_norm
(self)
ovi/modules/mmaudio/ext/bigvgan/models.py:247
Methodreparameterize
(self, mu, log_var)
ovi/modules/vae2_2.py:841
Functionresample
(x, f=[1, 1], mode='keep')
ovi/modules/mmaudio/ext/autoencoder/edm2_utils.py:79
Methodsample
(self, imgs, deterministic=False)
ovi/modules/vae.py:599
Methodsample
(self, imgs, deterministic=False)
ovi/modules/vae2_2.py:846
Methodscale_model_input
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Ar
ovi/utils/fm_solvers.py:800
Methodscale_model_input
Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A
ovi/utils/fm_solvers_unipc.py:741
Functionscore
(HW)
ovi/utils/processing_utils.py:50
Methodset_begin_index
Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index
ovi/utils/fm_solvers.py:216
Methodset_begin_index
Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde
ovi/utils/fm_solvers_unipc.py:149
Methodset_rope_params
(self)
ovi/modules/fusion.py:322
Methodset_timesteps
Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):
ovi/utils/fm_solvers_unipc.py:160
Functionshard_model
( model, device_id, param_dtype=torch.bfloat16, reduce_dtype=torch.float32, buffer_dtype=t
ovi/distributed_comms/distributed/fsdp.py:10
Methodsingle_fusion_block_forward
(self, vid_block, audio_block,
ovi/modules/fusion.py:161
Functionsp_parallel_dataloader_wrapper
(dataloader, device, train_batch_size, sp_size, train_sp_batch_size)
ovi/distributed_comms/communications.py:302
Functionspectral_normalize_torch
(magnitudes, norm_fn)
ovi/modules/mmaudio/ext/stft_converter_mel.py:14
Functionspectral_normalize_torch
(magnitudes, norm_fn)
ovi/modules/mmaudio/ext/stft_converter.py:14
Methodstep_index
The index counter for current timestep. It will increase 1 after each scheduler step.
ovi/utils/fm_solvers.py:202
Methodstep_index
The index counter for current timestep. It will increase 1 after each scheduler step.
ovi/utils/fm_solvers_unipc.py:135
Functionstr2bool
Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: 'no', 'false', 'f', 'n', '0'
ovi/utils/utils.py:134
Methodtrain
(self, mode: bool)
ovi/modules/mmaudio/features_utils.py:56
Functionusp_attn_forward
(self, x, seq_lens, grid_sizes,
ovi/distributed_comms/distributed/xdit_context_parallel.py:149
Functionusp_dit_forward
x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings each with s
ovi/distributed_comms/distributed/xdit_context_parallel.py:66
Methodvocode
(self, spec: torch.Tensor)
ovi/modules/mmaudio/ext/autoencoder/autoencoder.py:54
Methodwrapped_decode
(self, zs)
ovi/modules/vae2_2.py:1053
Methodwrapped_decode_stream
(self, z)
ovi/modules/vae.py:695
Methodwrapped_encode
(self, video)
ovi/modules/vae2_2.py:1065
Functionxlm_roberta_large
XLMRobertaLarge adapted from Huggingface.
ovi/modules/xlm_roberta.py:146
← previous401–478 of 478, ranked by callers