MCPcopy Create free account

hub / github.com/SkyworkAI/SkyReels-V2 / types & classes

Types & classes53 in github.com/SkyworkAI/SkyReels-V2

⨍ Functions 197◇ Types & classes 53
↓ 11 callersClassCausalConv3d
Causal 3d convolusion.
skyreels_v2_infer/modules/vae.py:17
↓ 7 callersClassT5LayerNorm
skyreels_v2_infer/modules/t5.py:51
↓ 6 callersClassFlowUniPCMultistepScheduler
`UniPCMultistepScheduler` is a training-free framework designed for the fast sampling of diffusion models. This model inherits from [`Schedu
skyreels_v2_infer/scheduler/fm_solvers_unipc.py:20
↓ 6 callersClassResidualBlock
skyreels_v2_infer/modules/vae.py:163
↓ 5 callersClassLayerNorm
skyreels_v2_infer/modules/clip.py:51
↓ 5 callersClassRMS_norm
skyreels_v2_infer/modules/vae.py:38
↓ 4 callersClassAttentionBlock
Causal self-attention with a single head.
skyreels_v2_infer/modules/vae.py:200
↓ 4 callersClassT5RelativeEmbedding
skyreels_v2_infer/modules/t5.py:188
↓ 4 callersClassWanLayerNorm
skyreels_v2_infer/modules/transformer.py:104
↓ 3 callersClassHuggingfaceTokenizer
skyreels_v2_infer/modules/tokenizers.py:38
↓ 3 callersClassPromptEnhancer
skyreels_v2_infer/pipelines/prompt_enhancer.py:25
↓ 3 callersClassT5Attention
skyreels_v2_infer/modules/t5.py:65
↓ 3 callersClassWanRMSNorm
skyreels_v2_infer/modules/transformer.py:86
↓ 2 callersClassQuickGELU
skyreels_v2_infer/modules/clip.py:46
↓ 2 callersClassResample
skyreels_v2_infer/modules/vae.py:61
↓ 2 callersClassStructuralCaptionDataset
skycaptioner_v1/scripts/vllm_fusion_caption.py:66
↓ 2 callersClassT5FeedForward
skyreels_v2_infer/modules/t5.py:117
↓ 2 callersClassUpsample
skyreels_v2_infer/modules/vae.py:53
↓ 2 callersClassVideoTextDataset
skycaptioner_v1/scripts/vllm_struct_caption.py:18
↓ 1 callersClassAttentionBlock
skyreels_v2_infer/modules/clip.py:108
↓ 1 callersClassAttentionBlock
skyreels_v2_infer/modules/xlm_roberta.py:48
↓ 1 callersClassAttentionPool
skyreels_v2_infer/modules/clip.py:154
↓ 1 callersClassCLIPModel
skyreels_v2_infer/modules/clip.py:488
↓ 1 callersClassDecoder3d
skyreels_v2_infer/modules/vae.py:337
↓ 1 callersClassDiffusionForcingPipeline
A pipeline for diffusion-based video generation tasks. This pipeline supports two main tasks: - Image-to-Video (i2v): Generates a video
skyreels_v2_infer/pipelines/diffusion_forcing_pipeline.py:25
↓ 1 callersClassEncoder3d
skyreels_v2_infer/modules/vae.py:239
↓ 1 callersClassFusionCaptioner
skycaptioner_v1/scripts/gradio_fusion_caption.py:50
↓ 1 callersClassGELU
skyreels_v2_infer/modules/t5.py:46
↓ 1 callersClassHead
skyreels_v2_infer/modules/transformer.py:347
↓ 1 callersClassImage2VideoPipeline
skyreels_v2_infer/pipelines/image2video_pipeline.py:38
↓ 1 callersClassMLPProj
skyreels_v2_infer/modules/transformer.py:382
↓ 1 callersClassSelfAttention
skyreels_v2_infer/modules/clip.py:56
↓ 1 callersClassSelfAttention
skyreels_v2_infer/modules/xlm_roberta.py:10
↓ 1 callersClassStructCaptioner
skycaptioner_v1/scripts/gradio_struct_caption.py:9
↓ 1 callersClassSwiGLU
skyreels_v2_infer/modules/clip.py:91
↓ 1 callersClassT5CrossAttention
skyreels_v2_infer/modules/t5.py:161
↓ 1 callersClassT5Decoder
skyreels_v2_infer/modules/t5.py:270
↓ 1 callersClassT5Encoder
skyreels_v2_infer/modules/t5.py:233
↓ 1 callersClassT5EncoderModel
skyreels_v2_infer/modules/t5.py:421
↓ 1 callersClassT5SelfAttention
skyreels_v2_infer/modules/t5.py:137
↓ 1 callersClassText2VideoPipeline
skyreels_v2_infer/pipelines/text2video_pipeline.py:17
↓ 1 callersClassVisionTransformer
skyreels_v2_infer/modules/clip.py:202
↓ 1 callersClassWanAttentionBlock
skyreels_v2_infer/modules/transformer.py:266
↓ 1 callersClassWanSelfAttention
skyreels_v2_infer/modules/transformer.py:116
↓ 1 callersClassWanVAE
skyreels_v2_infer/modules/vae.py:571
↓ 1 callersClassWanVAE_
skyreels_v2_infer/modules/vae.py:444
↓ 1 callersClassXLMRoberta
XLMRobertaModel with no pooler and no LM head.
skyreels_v2_infer/modules/xlm_roberta.py:72
↓ 1 callersClassXLMRobertaWithHead
skyreels_v2_infer/modules/clip.py:292
ClassT5Model
skyreels_v2_infer/modules/t5.py:316
ClassWanI2VCrossAttention
skyreels_v2_infer/modules/transformer.py:210
ClassWanModel
r""" Wan diffusion backbone supporting both text-to-video and image-to-video.
skyreels_v2_infer/modules/transformer.py:399
ClassWanT2VCrossAttention
skyreels_v2_infer/modules/transformer.py:186
ClassXLMRobertaCLIP
skyreels_v2_infer/modules/clip.py:316