MCPcopy Create free account

hub / github.com/360CVGroup/FancyVideo / types & classes

Types & classes62 in github.com/360CVGroup/FancyVideo

⨍ Functions 243◇ Types & classes 62
↓ 7 callersClassInflatedConv3d
fancyvideo/models/resnet.py:10
↓ 6 callersClassResnetBlock3D
fancyvideo/models/resnet.py:112
↓ 5 callersClassLayerNorm
Subclass torch's LayerNorm to handle fp16.
fancyvideo/models/long_clip/model_longclip.py:157
↓ 3 callersClassCrossAttention
A cross attention layer. Parameters: query_dim (`int`): The number of channels in the query. cross_attention_dim (`int`, *op
fancyvideo/models/ctgm/attention.py:33
↓ 3 callersClassInflatedGroupNorm
fancyvideo/models/resnet.py:21
↓ 3 callersClassResnetBlock3D
fancyvideo/models/cv_vae/vae_models.py:349
↓ 3 callersClassTransformer3DModel
fancyvideo/models/ctgm/attention.py:394
↓ 2 callersClassBottleneck
fancyvideo/models/long_clip/model_longclip.py:10
↓ 2 callersClassCondEmbedding
fancyvideo/models/unet.py:44
↓ 2 callersClassDownsample3D
fancyvideo/models/resnet.py:86
↓ 2 callersClassTransformer
fancyvideo/models/long_clip/model_longclip.py:195
↓ 2 callersClassUpsample3D
fancyvideo/models/resnet.py:32
↓ 1 callersClassAnimationPipelineOutput
fancyvideo/pipelines/pipeline_animation_vae_2d.py:42
↓ 1 callersClassAnimationPipelineOutput
fancyvideo/pipelines/pipeline_animation_vae_3d.py:42
↓ 1 callersClassAttentionPool2d
fancyvideo/models/long_clip/model_longclip.py:58
↓ 1 callersClassAttnBlock
fancyvideo/models/cv_vae/vae_models.py:433
↓ 1 callersClassBasicTransformerBlock
fancyvideo/models/ctgm/attention.py:608
↓ 1 callersClassCLIP
fancyvideo/models/long_clip/model_longclip.py:243
↓ 1 callersClassConv2dWithExtraDim
fancyvideo/models/cv_vae/vae_models.py:337
↓ 1 callersClassCrossAttnDownBlock3D
fancyvideo/models/unet_blocks.py:316
↓ 1 callersClassCrossAttnUpBlock3D
fancyvideo/models/unet_blocks.py:599
↓ 1 callersClassDecoder
fancyvideo/models/cv_vae/vae_models.py:867
↓ 1 callersClassDownBlock3D
fancyvideo/models/unet_blocks.py:489
↓ 1 callersClassDownsample3D
fancyvideo/models/cv_vae/vae_models.py:244
↓ 1 callersClassEncoder
fancyvideo/models/cv_vae/vae_models.py:720
↓ 1 callersClassInferPipeline
fancyvideo/pipelines/fancyvideo_infer_pipeline.py:96
↓ 1 callersClassInflated
fancyvideo/pipelines/fancyvideo_infer_pipeline.py:258
↓ 1 callersClassLinAttnBlock
to match AttnBlock usage
fancyvideo/models/cv_vae/vae_models.py:419
↓ 1 callersClassMemoryEfficientAttnBlock
Uses xformers efficient implementation, see https://github.com/MatthieuTPHR/diffusers/blob/d80b531ff8060ec1ea982b65a1b8df70f73aa67c/src/diffu
fancyvideo/models/cv_vae/vae_models.py:479
↓ 1 callersClassMemoryEfficientAttnVideoBlock
Uses xformers efficient implementation, see https://github.com/MatthieuTPHR/diffusers/blob/d80b531ff8060ec1ea982b65a1b8df70f73aa67c/src/diffu
fancyvideo/models/cv_vae/vae_models.py:558
↓ 1 callersClassMemoryEfficientCrossAttentionWrapper
fancyvideo/models/cv_vae/vae_models.py:673
↓ 1 callersClassMish
fancyvideo/models/resnet.py:218
↓ 1 callersClassModifiedResNet
A ResNet class that is similar to torchvision's but contains the following changes: - There are now 3 "stem" convolutions as opposed to 1, wi
fancyvideo/models/long_clip/model_longclip.py:94
↓ 1 callersClassPositionalEncoding
fancyvideo/models/motion_module.py:228
↓ 1 callersClassQuickGELU
fancyvideo/models/long_clip/model_longclip.py:166
↓ 1 callersClassResidualAttentionBlock
fancyvideo/models/long_clip/model_longclip.py:171
↓ 1 callersClassTemporalTransformer3DModel
fancyvideo/models/motion_module.py:88
↓ 1 callersClassTemporalTransformer3DModel
fancyvideo/models/ctgm/temporal_cross_module.py:97
↓ 1 callersClassTemporalTransformerBlock
fancyvideo/models/motion_module.py:164
↓ 1 callersClassTemporalTransformerBlock
fancyvideo/models/ctgm/temporal_cross_module.py:173
↓ 1 callersClassTransformer3DModelOutput
fancyvideo/models/ctgm/attention.py:30
↓ 1 callersClassUNet3DConditionOutput
fancyvideo/models/unet.py:35
↓ 1 callersClassUNetMidBlock3DCrossAttn
fancyvideo/models/unet_blocks.py:189
↓ 1 callersClassUpBlock3D
fancyvideo/models/unet_blocks.py:768
↓ 1 callersClassUpsample3D
fancyvideo/models/cv_vae/vae_models.py:204
↓ 1 callersClassVanillaTemporalModule
fancyvideo/models/motion_module.py:50
↓ 1 callersClassVanillaTemporalModule
fancyvideo/models/ctgm/temporal_cross_module.py:52
↓ 1 callersClassVersatileAttention
fancyvideo/models/motion_module.py:249
↓ 1 callersClassVersatileAttention
fancyvideo/models/ctgm/temporal_cross_module.py:258
↓ 1 callersClassVisionTransformer
fancyvideo/models/long_clip/model_longclip.py:206
ClassAnimationFreeInitPipelineOutput
fancyvideo/pipelines/pipeline_animation_vae_2d.py:46
ClassAnimationFreeInitPipelineOutput
fancyvideo/pipelines/pipeline_animation_vae_3d.py:46
ClassAnimationPipeline
fancyvideo/pipelines/pipeline_animation_vae_2d.py:51
ClassAnimationPipeline
fancyvideo/pipelines/pipeline_animation_vae_3d.py:51
ClassCVVAEModel
fancyvideo/models/cv_vae/modeling_vae.py:13
ClassCausalConv3d
fancyvideo/models/cv_vae/vae_models.py:272
ClassLinearAttention
fancyvideo/models/cv_vae/vae_models.py:63
ClassMemoryEfficientCrossAttention
fancyvideo/models/cv_vae/vae_models.py:85
ClassSimpleTokenizer
fancyvideo/models/long_clip/simple_tokenizer.py:62
ClassTemporalTransformer3DModelOutput
fancyvideo/models/motion_module.py:28
ClassTemporalTransformer3DModelOutput
fancyvideo/models/ctgm/temporal_cross_module.py:29
ClassUNet3DConditionModel
fancyvideo/models/unet.py:63