Types & classes — github.com/antgroup/echomimic_v3

CodeHub MCPcopy Create free account

hub / github.com/antgroup/echomimic_v3 / types & classes

Types & classes66 in github.com/antgroup/echomimic_v3

⨍ Functions 301◇ Types & classes 66

↓ 11 callersClassCausalConv3d

Causal 3d convolusion.

src/wan_vae.py:23

↓ 6 callersClassResidualBlock

src/wan_vae.py:192

↓ 6 callersClassT5LayerNorm

src/wan_text_encoder.py:44

↓ 5 callersClassLayerNorm

src/wan_image_encoder.py:49

↓ 5 callersClassRMS_norm

src/wan_vae.py:45

↓ 5 callersClassWanRMSNorm

src/wan_transformer3d_audio_2512.py:613

↓ 5 callersClassWanRMSNorm

src/wan_transformer3d_audio.py:553

↓ 4 callersClassAttentionBlock

Causal self-attention with a single head.

src/wan_vae.py:229

↓ 4 callersClassWanLayerNorm

src/wan_transformer3d_audio_2512.py:632

↓ 4 callersClassWanLayerNorm

src/wan_transformer3d_audio.py:572

↓ 3 callersClassT5Attention

src/wan_text_encoder.py:59

↓ 3 callersClassT5RelativeEmbedding

src/wan_text_encoder.py:208

↓ 3 callersClassWanFunInpaintAudioPipeline

r""" Pipeline for text-to-video generation using Wan. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for

src/pipeline_wan_fun_inpaint_audio.py:155

↓ 2 callersClassQuickGELU

src/wan_image_encoder.py:43

↓ 2 callersClassResample

src/wan_vae.py:72

↓ 2 callersClassSimpleAdapter

src/wan_camera_adapter.py:4

↓ 2 callersClassT5FeedForward

src/wan_text_encoder.py:112

↓ 2 callersClassTeaCache

Timestep Embedding Aware Cache, a training-free caching approach that estimates and leverages the fluctuating differences among model outputs

src/cache_utils.py:19

↓ 2 callersClassUpsample

src/wan_vae.py:63

↓ 1 callersClassAttentionBlock

src/wan_xlm_roberta.py:49

↓ 1 callersClassAttentionBlock

src/wan_image_encoder.py:114

↓ 1 callersClassAttentionPool

src/wan_image_encoder.py:158

↓ 1 callersClassAudioProjModel

src/wan_transformer3d_audio_2512.py:176

↓ 1 callersClassAudioProjModel

src/wan_transformer3d_audio.py:153

↓ 1 callersClassAutoencoderKLWan_

src/wan_vae.py:489

↓ 1 callersClassConfig

↓ 1 callersClassConfig

infer_preview.py:44

↓ 1 callersClassConfig

↓ 1 callersClassDecoder3d

src/wan_vae.py:375

↓ 1 callersClassEncoder3d

src/wan_vae.py:271

↓ 1 callersClassGELU

src/wan_text_encoder.py:38

↓ 1 callersClassHead

src/wan_transformer3d_audio_2512.py:970

↓ 1 callersClassHead

src/wan_transformer3d_audio.py:920

↓ 1 callersClassMLPProj

src/wan_transformer3d_audio_2512.py:998

↓ 1 callersClassMLPProj

src/wan_transformer3d_audio.py:948

↓ 1 callersClassResidualBlock

src/wan_camera_adapter.py:42

↓ 1 callersClassSelfAttention

src/wan_xlm_roberta.py:10

↓ 1 callersClassSelfAttention

src/wan_image_encoder.py:55

↓ 1 callersClassSwiGLU

src/wan_image_encoder.py:96

↓ 1 callersClassT5SelfAttention

src/wan_text_encoder.py:133

↓ 1 callersClassVisionTransformer

src/wan_image_encoder.py:211

↓ 1 callersClassWanAttentionBlock

src/wan_transformer3d_audio_2512.py:886

↓ 1 callersClassWanAttentionBlock

src/wan_transformer3d_audio.py:836

↓ 1 callersClassWanFunInpaintAudioPipeline

r""" Pipeline for text-to-video generation using Wan. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for

src/pipeline_wan_fun_inpaint_audio_2512.py:159

↓ 1 callersClassWanPipelineOutput

r""" Output class for CogVideo pipelines. Args: video (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): Lis

src/pipeline_wan_fun_inpaint_audio.py:141

↓ 1 callersClassWanPipelineOutput

r""" Output class for CogVideo pipelines. Args: video (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): Lis

src/pipeline_wan_fun_inpaint_audio_2512.py:145

↓ 1 callersClassWanSelfAttention

src/wan_transformer3d_audio_2512.py:645

↓ 1 callersClassWanSelfAttention

src/wan_transformer3d_audio.py:585

↓ 1 callersClassXLMRoberta

XLMRobertaModel with no pooler and no LM head.

src/wan_xlm_roberta.py:76

↓ 1 callersClassXLMRobertaWithHead

src/wan_image_encoder.py:305

ClassAutoencoderKLWan

src/wan_vae.py:623

src/wan_image_encoder.py:503

ClassFlowDPMSolverMultistepScheduler

`FlowDPMSolverMultistepScheduler` is a fast dedicated high-order solver for diffusion ODEs. This model inherits from [`SchedulerMixin`] and [

src/fm_solvers.py:69

ClassFlowUniPCMultistepScheduler

`UniPCMultistepScheduler` is a training-free framework designed for the fast sampling of diffusion models. This model inherits from [`Schedu

src/fm_solvers_unipc.py:20

ClassT5CrossAttention

src/wan_text_encoder.py:166

ClassWanI2VCrossAttention

src/wan_transformer3d_audio_2512.py:734

ClassWanI2VCrossAttention

src/wan_transformer3d_audio.py:674

ClassWanI2VCrossAttentionAudio

src/wan_transformer3d_audio_2512.py:789

ClassWanI2VCrossAttentionAudio

src/wan_transformer3d_audio.py:731

ClassWanT2VCrossAttention

src/wan_transformer3d_audio_2512.py:703

ClassWanT2VCrossAttention

src/wan_transformer3d_audio.py:643

ClassWanT5EncoderModel

src/wan_text_encoder.py:256

ClassWanTransformerAudioMask3DModel

r""" Wan diffusion backbone supporting both text-to-video and image-to-video.

src/wan_transformer3d_audio_2512.py:1014

ClassWanTransformerAudioMask3DModel

r""" Wan diffusion backbone supporting both text-to-video and image-to-video.

src/wan_transformer3d_audio.py:962

ClassWav2Vec2Model

src/wav2vec2.py:28

ClassXLMRobertaCLIP

src/wan_image_encoder.py:330