MCPcopy Create free account

hub / github.com/MotrixLab/ViMoGen / types & classes

Types & classes71 in github.com/MotrixLab/ViMoGen

⨍ Functions 457◇ Types & classes 71
↓ 7 callersClassT5LayerNorm
models/transformer/wan/modules/t5.py:53
↓ 7 callersClassWanLayerNorm
models/transformer/wan/modules/tm2m_model.py:250
↓ 4 callersClassT5RelativeEmbedding
models/transformer/wan/modules/t5.py:221
↓ 4 callersClassWanLayerNorm
models/transformer/wan/modules/t2m_model.py:249
↓ 3 callersClassHead
models/transformer/wan/modules/t2m_model.py:454
↓ 3 callersClassT5Attention
models/transformer/wan/modules/t5.py:69
↓ 3 callersClassWanRMSNorm
models/transformer/wan/modules/t2m_model.py:234
↓ 2 callersClassFlopEstimator2D1DNotExact
datasets/bucket_config.py:166
↓ 2 callersClassHuggingfaceTokenizer
models/transformer/wan/modules/tokenizers.py:37
↓ 2 callersClassMBench
MBench: Motion generation benchmark for evaluating human motion videos
mbench/__init__.py:13
↓ 2 callersClassPositionalEncoding
models/transformer/wan/modules/tm2m_model.py:535
↓ 2 callersClassT5FeedForward
models/transformer/wan/modules/t5.py:123
↓ 2 callersClassWanRMSNorm
models/transformer/wan/modules/tm2m_model.py:235
↓ 2 callersClassWanSelfAttention
models/transformer/wan/modules/tm2m_model.py:259
↓ 1 callersClassBucket
datasets/bucket.py:29
↓ 1 callersClassBucketFactory
datasets/multi_resolution_sampler.py:10
↓ 1 callersClassCogVideoXDDIMScheduler
trainer/scheduler.py:58
↓ 1 callersClassCogVideoXDPMScheduler
trainer/scheduler.py:66
↓ 1 callersClassDDIMScheduler
trainer/scheduler.py:62
↓ 1 callersClassDistributedFlopBalanceSampler
datasets/multi_resolution_sampler.py:92
↓ 1 callersClassDummyDataset
trainer/__init__.py:14
↓ 1 callersClassFlowMatchScheduler
trainer/scheduler.py:153
↓ 1 callersClassGELU
models/transformer/wan/modules/t5.py:46
↓ 1 callersClassHead
models/transformer/wan/modules/tm2m_model.py:496
↓ 1 callersClassMLPProj
models/transformer/wan/modules/tm2m_model.py:521
↓ 1 callersClassMLPProj
models/transformer/wan/modules/t2m_model.py:479
↓ 1 callersClassMultiProcessAdapter
parallel/logging.py:10
↓ 1 callersClassPositionalEncoding
models/transformer/wan/modules/t2m_model.py:493
↓ 1 callersClassStatefulDistributedSampler
datasets/sampler.py:27
↓ 1 callersClassT5CrossAttention
models/transformer/wan/modules/t5.py:178
↓ 1 callersClassT5Decoder
models/transformer/wan/modules/t5.py:315
↓ 1 callersClassT5Encoder
models/transformer/wan/modules/t5.py:267
↓ 1 callersClassT5EncoderModel
models/transformer/wan/modules/t5.py:472
↓ 1 callersClassT5SelfAttention
models/transformer/wan/modules/t5.py:144
↓ 1 callersClassTbTracker
parallel/logging.py:78
↓ 1 callersClassTextDataset
models/transformer/wan/text_encoding_batch.py:8
↓ 1 callersClassTimer
trainer/base_trainer.py:356
↓ 1 callersClassTrainerBase
base trainer with data parallel and tensor parallel functionalities.
trainer/base_trainer.py:27
↓ 1 callersClassWanAttentionBlock
models/transformer/wan/modules/tm2m_model.py:337
↓ 1 callersClassWanAttentionBlock
models/transformer/wan/modules/t2m_model.py:384
↓ 1 callersClassWanAttentionBlock_SAonly
models/transformer/wan/modules/tm2m_model.py:439
↓ 1 callersClassWanModelStateDictConverter
models/transformer/wan/modules/tm2m_model.py:789
↓ 1 callersClassWanModelStateDictConverter
models/transformer/wan/modules/t2m_model.py:709
↓ 1 callersClassWanModelT2M
models/transformer/wan/modules/t2m_model.py:513
↓ 1 callersClassWanModelTM2M
models/transformer/wan/modules/tm2m_model.py:555
↓ 1 callersClassWanSelfAttention
models/transformer/wan/modules/t2m_model.py:258
↓ 1 callersClassWanT2VCrossAttention
models/transformer/wan/modules/tm2m_model.py:309
ClassAppState
This is a useful wrapper for checkpointing the Application State. Since this object is compliant with the Stateful protocol, DCP will automaticall
trainer/base_trainer.py:315
ClassBatchDistributedSampler
Used with BatchDataset; Suppose len_buffer == 5, num_buffers == 6, #GPUs. == 3, then. | buffer {i} | buffer {i+1} -
datasets/sampler.py:321
ClassBucketConfig
datasets/bucket_config.py:211
ClassBucketConfig3AR
datasets/bucket_config.py:384
ClassBucketConfigFromSideList
datasets/bucket_config.py:323
ClassBucketConfigHardCoded1
datasets/bucket_config.py:267
ClassBucketConfigHardCoded2
datasets/bucket_config.py:283
ClassBucketConfigHardCoded3
datasets/bucket_config.py:300
ClassDefaultBucketConfig
datasets/bucket_config.py:339
ClassDefaultBucketConfig3ARNotExact
datasets/bucket_config.py:406
ClassDefaultBucketConfigNotExact
datasets/bucket_config.py:361
ClassFlopEstimator
datasets/bucket_config.py:112
ClassFlopEstimatorExact
datasets/bucket_config.py:131
ClassMBenchWiRefMotion
datasets/video_datasets.py:221
ClassSD3RectFlow
trainer/sd3_scheduler.py:11
ClassT5Model
models/transformer/wan/modules/t5.py:372
ClassTimestepSamplerMP
trainer/scheduler.py:70
ClassVariableVideoBatchSampler
datasets/sampler.py:60
ClassWanI2VCrossAttention
models/transformer/wan/modules/t2m_model.py:334
ClassWanMotionTensorDatasetWiRefMotion
datasets/video_datasets.py:8
ClassWanMotionTensorDatasetWiRefMotionM2M
Dataset variant for motion-to-motion refinement where text embeddings are unused. Reuses all logic from WanMotionTensorDatasetWiRefMotion but
datasets/video_datasets.py:207
ClassWanT2VCrossAttention
models/transformer/wan/modules/t2m_model.py:310
ClassWeakPerspectiveCamera
mbench/render.py:24
ClassZoeScheduler
trainer/scheduler.py:10