MCPcopy Create free account

hub / github.com/character-ai/Ovi / types & classes

Types & classes112 in github.com/character-ai/Ovi

⨍ Functions 478◇ Types & classes 112
↓ 13 callersClassMPConv1D
ovi/modules/mmaudio/ext/autoencoder/edm2_utils.py:142
↓ 11 callersClassCausalConv3d
Causal 3d convolusion.
ovi/modules/vae.py:17
↓ 11 callersClassCausalConv3d
Causal 3d convolusion.
ovi/modules/vae2_2.py:17
↓ 7 callersClassT5LayerNorm
ovi/modules/t5.py:53
↓ 6 callersClassActivation1d
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/act.py:8
↓ 6 callersClassResidualBlock
ovi/modules/vae.py:186
↓ 6 callersClassResidualBlock
ovi/modules/vae2_2.py:193
↓ 6 callersClassResnetBlock1D
ovi/modules/mmaudio/ext/autoencoder/vae_modules.py:14
↓ 6 callersClassWanLayerNorm
ovi/modules/model.py:185
↓ 5 callersClassActivation1d
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/act.py:9
↓ 5 callersClassLayerNorm
ovi/modules/clip.py:47
↓ 5 callersClassPromptOutput
ovi/utils/prompt_extend.py:101
↓ 5 callersClassRMS_norm
ovi/modules/vae.py:39
↓ 5 callersClassRMS_norm
ovi/modules/vae2_2.py:45
↓ 5 callersClassWanRMSNorm
ovi/modules/model.py:166
↓ 4 callersClassAttentionBlock
Causal self-attention with a single head.
ovi/modules/vae.py:223
↓ 4 callersClassAttnBlock1D
ovi/modules/mmaudio/ext/autoencoder/vae_modules.py:54
↓ 4 callersClassChannelLastConv1d
ovi/modules/model.py:110
↓ 4 callersClassT5RelativeEmbedding
ovi/modules/t5.py:221
↓ 3 callersClassHuggingfaceTokenizer
ovi/modules/tokenizers.py:37
↓ 3 callersClassT5Attention
ovi/modules/t5.py:69
↓ 2 callersClassAttentionBlock
Causal self-attention with a single head.
ovi/modules/vae2_2.py:238
↓ 2 callersClassDashScopePromptExpander
ovi/utils/prompt_extend.py:157
↓ 2 callersClassDownSample1d
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/resample.py:37
↓ 2 callersClassFeaturesUtils
ovi/modules/mmaudio/features_utils.py:33
↓ 2 callersClassFusionModel
ovi/modules/fusion.py:9
↓ 2 callersClassMelConverter
ovi/modules/mmaudio/ext/mel_converter.py:18
↓ 2 callersClassOviFusionEngine
ovi/ovi_fusion_engine.py:51
↓ 2 callersClassQuickGELU
ovi/modules/clip.py:41
↓ 2 callersClassQwenPromptExpander
ovi/utils/prompt_extend.py:300
↓ 2 callersClassResample
ovi/modules/vae.py:66
↓ 2 callersClassResample
ovi/modules/vae2_2.py:71
↓ 2 callersClassT5FeedForward
ovi/modules/t5.py:123
↓ 2 callersClassUpSample1d
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/resample.py:10
↓ 2 callersClassUpsample
ovi/modules/vae.py:57
↓ 2 callersClassUpsample
ovi/modules/vae2_2.py:62
↓ 2 callersClassVAE
ovi/modules/mmaudio/ext/autoencoder/vae.py:66
↓ 2 callersClassWanModel
r""" Wan diffusion backbone supporting both text-to-video and image-to-video, text-to-audio.
ovi/modules/model.py:520
↓ 1 callersClassAttentionBlock
ovi/modules/clip.py:113
↓ 1 callersClassAttentionBlock
ovi/modules/xlm_roberta.py:49
↓ 1 callersClassAttentionPool
ovi/modules/clip.py:157
↓ 1 callersClassAttrDict
ovi/modules/mmaudio/ext/bigvgan_v2/env.py:8
↓ 1 callersClassAutoEncoderModule
ovi/modules/mmaudio/ext/autoencoder/autoencoder.py:15
↓ 1 callersClassAvgDown3D
ovi/modules/vae2_2.py:316
↓ 1 callersClassBigVGAN
ovi/modules/mmaudio/ext/bigvgan/bigvgan.py:12
↓ 1 callersClassBigVGANVocoder
ovi/modules/mmaudio/ext/bigvgan/models.py:169
↓ 1 callersClassCOMM_INFO
ovi/distributed_comms/parallel_states.py:6
↓ 1 callersClassConvMLP
ovi/modules/model.py:119
↓ 1 callersClassDecoder1D
ovi/modules/mmaudio/ext/autoencoder/vae.py:266
↓ 1 callersClassDecoder3d
ovi/modules/vae.py:369
↓ 1 callersClassDecoder3d
ovi/modules/vae2_2.py:616
↓ 1 callersClassDiagonalGaussianDistribution
ovi/modules/mmaudio/ext/autoencoder/distributions.py:6
↓ 1 callersClassDownSample1d
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/resample.py:36
↓ 1 callersClassDown_ResidualBlock
ovi/modules/vae2_2.py:415
↓ 1 callersClassDownsample1D
ovi/modules/mmaudio/ext/autoencoder/vae_modules.py:97
↓ 1 callersClassDupUp3D
ovi/modules/vae2_2.py:370
↓ 1 callersClassEncoder1D
ovi/modules/mmaudio/ext/autoencoder/vae.py:170
↓ 1 callersClassEncoder3d
ovi/modules/vae.py:265
↓ 1 callersClassEncoder3d
ovi/modules/vae2_2.py:500
↓ 1 callersClassFlowDPMSolverMultistepScheduler
`FlowDPMSolverMultistepScheduler` is a fast dedicated high-order solver for diffusion ODEs. This model inherits from [`SchedulerMixin`] and [
ovi/utils/fm_solvers.py:69
↓ 1 callersClassFlowUniPCMultistepScheduler
`UniPCMultistepScheduler` is a training-free framework designed for the fast sampling of diffusion models. This model inherits from [`Schedu
ovi/utils/fm_solvers_unipc.py:20
↓ 1 callersClassGELU
ovi/modules/t5.py:46
↓ 1 callersClassHead
ovi/modules/model.py:474
↓ 1 callersClassLowPassFilter1d
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/filter.py:65
↓ 1 callersClassLowPassFilter1d
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/filter.py:60
↓ 1 callersClassMLPProj
ovi/modules/model.py:505
↓ 1 callersClassModulationAdd
ovi/modules/model.py:368
↓ 1 callersClassSTFTConverter
ovi/modules/mmaudio/ext/stft_converter_mel.py:19
↓ 1 callersClassSTFTConverter
ovi/modules/mmaudio/ext/stft_converter.py:19
↓ 1 callersClassSelfAttention
ovi/modules/clip.py:53
↓ 1 callersClassSelfAttention
ovi/modules/xlm_roberta.py:10
↓ 1 callersClassSwiGLU
ovi/modules/clip.py:95
↓ 1 callersClassT5CrossAttention
ovi/modules/t5.py:178
↓ 1 callersClassT5Decoder
ovi/modules/t5.py:315
↓ 1 callersClassT5Encoder
ovi/modules/t5.py:267
↓ 1 callersClassT5EncoderModel
ovi/modules/t5.py:472
↓ 1 callersClassT5SelfAttention
ovi/modules/t5.py:144
↓ 1 callersClassUpSample1d
ovi/modules/mmaudio/ext/bigvgan/alias_free_torch/resample.py:10
↓ 1 callersClassUp_ResidualBlock
ovi/modules/vae2_2.py:455
↓ 1 callersClassUpsample1D
ovi/modules/mmaudio/ext/autoencoder/vae_modules.py:82
↓ 1 callersClassVisionTransformer
ovi/modules/clip.py:212
↓ 1 callersClassWan2_2_VAE
ovi/modules/vae2_2.py:888
↓ 1 callersClassWanAttentionBlock
ovi/modules/model.py:376
↓ 1 callersClassWanI2VCrossAttention
ovi/modules/model.py:297
↓ 1 callersClassWanSelfAttention
ovi/modules/model.py:198
↓ 1 callersClassWanT2VCrossAttention
ovi/modules/model.py:268
↓ 1 callersClassWanVAE_
ovi/modules/vae.py:483
↓ 1 callersClassWanVAE_
ovi/modules/vae2_2.py:734
↓ 1 callersClassXLMRoberta
XLMRobertaModel with no pooler and no LM head.
ovi/modules/xlm_roberta.py:76
↓ 1 callersClassXLMRobertaWithHead
ovi/modules/clip.py:306
ClassAMPBlock1
AMPBlock applies Snake / SnakeBeta activation functions with trainable parameters that control periodicity, defined for each layer. AMPBlock1
ovi/modules/mmaudio/ext/bigvgan_v2/bigvgan.py:32
ClassAMPBlock1
ovi/modules/mmaudio/ext/bigvgan/models.py:20
ClassAMPBlock2
AMPBlock applies Snake / SnakeBeta activation functions with trainable parameters that control periodicity, defined for each layer. Unlike AM
ovi/modules/mmaudio/ext/bigvgan_v2/bigvgan.py:130
ClassAMPBlock2
ovi/modules/mmaudio/ext/bigvgan/models.py:113
ClassActivation1d
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/activation1d.py:35
ClassAttrDict
ovi/modules/mmaudio/ext/bigvgan/env.py:8
ClassBigVGAN
BigVGAN is a neural vocoder model that applies anti-aliased periodic activation for residual blocks (resblocks). New in BigVGAN-v2: it can op
ovi/modules/mmaudio/ext/bigvgan_v2/bigvgan.py:209
ClassCLIPModel
ovi/modules/clip.py:504
ClassFusedAntiAliasActivation
Assumes filter size 12, replication padding on upsampling/downsampling, and logscale alpha/beta parameters as inputs. The hyperparameters are
ovi/modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/activation1d.py:14
ClassMPSiLU
ovi/modules/mmaudio/ext/autoencoder/edm2_utils.py:110
next →1–100 of 112, ranked by callers