MCPcopy Create free account

hub / github.com/OpenImagingLab/FlashVSR / types & classes

Types & classes521 in github.com/OpenImagingLab/FlashVSR

⨍ Functions 2,110◇ Types & classes 521
↓ 141 callersClassResnetBlock
diffsynth/models/sd_unet.py:94
↓ 105 callersClassPushBlock
diffsynth/models/sd_unet.py:211
↓ 55 callersClassAttentionBlock
diffsynth/models/sd_unet.py:126
↓ 38 callersClassPopMixBlock
diffsynth/models/svd_unet.py:217
↓ 36 callersClassTemporalBlock
diffsynth/models/sd_motion.py:52
↓ 33 callersClassPopBlock
diffsynth/models/sd_unet.py:220
↓ 32 callersClassResnet3DBlock
diffsynth/models/cog_vae.py:128
↓ 22 callersClassTemporalResnetBlock
diffsynth/models/svd_unet.py:6
↓ 19 callersClassDownSampler
diffsynth/models/sd_unet.py:70
↓ 17 callersClassUpSampler
diffsynth/models/sd_unet.py:83
↓ 16 callersClassTemporalAttentionBlock
diffsynth/models/svd_unet.py:138
↓ 14 callersClassCausalConv3d
Causal 3d convolusion.
diffsynth/models/wan_video_vae.py:33
↓ 14 callersClassTemporalResnetBlock
diffsynth/models/svd_vae_decoder.py:45
↓ 12 callersClassAttention
diffsynth/models/attention.py:15
↓ 10 callersClassEnhancedDDIMScheduler
diffsynth/schedulers/ddim.py:4
↓ 9 callersClassAdaLayerNorm
diffsynth/models/sd3_dit.py:69
↓ 9 callersClassFlowMatchScheduler
diffsynth/schedulers/flow_match.py:5
↓ 9 callersClassMemBlock
examples/WanVSR/utils/TCDecoder.py:41
↓ 9 callersClassPyramidPatchMatcher
diffsynth/extensions/FastBlend/patch_match.py:205
↓ 9 callersClassRMSNorm
diffsynth/models/sd3_dit.py:8
↓ 9 callersClassTileWorker
diffsynth/models/tiler.py:5
↓ 9 callersClassTimestepEmbeddings
diffsynth/models/sd3_dit.py:54
↓ 9 callersClassTimesteps
diffsynth/models/sd_unet.py:6
↓ 8 callersClassCausalConvChannelLast
diffsynth/models/stepvideo_vae.py:414
↓ 8 callersClassRMSNorm
diffsynth/models/flux_dit.py:519
↓ 7 callersClassCachedConv3d
diffsynth/models/cog_vae.py:169
↓ 7 callersClassModelManager
diffsynth/models/model_manager.py:316
↓ 6 callersClassBaseGroupNorm
diffsynth/models/stepvideo_vae.py:21
↓ 6 callersClassCausalConv
diffsynth/models/stepvideo_vae.py:226
↓ 6 callersClassCausalConv3d
diffsynth/models/hunyuan_video_vae_decoder.py:10
↓ 6 callersClassCausalConvAfterNorm
diffsynth/models/stepvideo_vae.py:438
↓ 6 callersClassRMSNorm
diffsynth/models/hunyuan_video_dit.py:732
↓ 6 callersClassResidualBlock
diffsynth/models/wan_video_vae.py:199
↓ 6 callersClassResnet3DBlock
diffsynth/models/stepvideo_vae.py:498
↓ 5 callersClassLayerNorm
diffsynth/models/wan_video_image_encoder.py:228
↓ 5 callersClassRMS_norm
diffsynth/models/wan_video_vae.py:56
↓ 4 callersClassAnnotator
diffsynth/controlnets/processors.py:8
↓ 4 callersClassAttentionBlock
Causal self-attention with a single head.
diffsynth/models/wan_video_vae.py:236
↓ 4 callersClassCLIPEncoderLayer
diffsynth/models/sd_text_encoder.py:5
↓ 4 callersClassCausalConv3d
Causal 3d convolusion.
examples/WanVSR/utils/utils.py:30
↓ 4 callersClassControlNetUnit
diffsynth/controlnets/controlnet_unit.py:14
↓ 4 callersClassFP32_Layernorm
diffsynth/models/hunyuan_dit.py:55
↓ 4 callersClassFP32_SiLU
diffsynth/models/hunyuan_dit.py:61
↓ 4 callersClassGEGLU
diffsynth/models/sd_unet.py:20
↓ 4 callersClassIFBlock
diffsynth/extensions/RIFE/__init__.py:34
↓ 4 callersClassJointAttention
diffsynth/models/sd3_dit.py:96
↓ 4 callersClassLayerScale
diffsynth/extensions/ImageQualityMetric/open_clip/transformer.py:37
↓ 4 callersClassQuantizedLinear
diffsynth/models/kolors_text_encoder.py:158
↓ 4 callersClassRMSNorm
diffsynth/models/wan_video_dit.py:276
↓ 4 callersClassRMSNorm
diffsynth/models/stepvideo_dit.py:20
↓ 4 callersClassRMS_norm
examples/WanVSR/utils/utils.py:13
↓ 4 callersClassResnetBlockCausal3D
diffsynth/models/hunyuan_video_vae_decoder.py:64
↓ 4 callersClassTimestepEmbedding
diffsynth/models/stepvideo_dit.py:163
↓ 4 callersClassVAEAttentionBlock
diffsynth/models/sd_vae_decoder.py:7
↓ 4 callersClassVideoData
diffsynth/extensions/FastBlend/data.py:96
↓ 3 callersClassBuffer_LQ4x_Proj
examples/WanVSR/utils/utils.py:67
↓ 3 callersClassCLIPTextCfg
diffsynth/extensions/ImageQualityMetric/open_clip/model.py:49
↓ 3 callersClassCLIPVisionCfg
diffsynth/extensions/ImageQualityMetric/open_clip/model.py:24
↓ 3 callersClassCausal_LQ4x_Proj
examples/WanVSR/utils/utils.py:166
↓ 3 callersClassCogAdaLayerNorm
diffsynth/models/cog_dit.py:23
↓ 3 callersClassCogVideoXSpatialNorm3D
diffsynth/models/cog_vae.py:103
↓ 3 callersClassDownsample3D
diffsynth/models/cog_vae.py:7
↓ 3 callersClassHFTokenizer
HuggingFace tokenizer wrapper
diffsynth/extensions/ImageQualityMetric/open_clip/tokenizer.py:188
↓ 3 callersClassLayerNorm
diffsynth/extensions/ImageQualityMetric/trainer/models/cross_modeling.py:18
↓ 3 callersClassModulateDiT
diffsynth/models/hunyuan_video_dit.py:275
↓ 3 callersClassMultiControlNetManager
diffsynth/controlnets/controlnet_unit.py:21
↓ 3 callersClassResidualDenseBlock
diffsynth/extensions/ESRGAN/__init__.py:7
↓ 3 callersClassT5LayerNorm
diffsynth/models/wan_video_text_encoder.py:22
↓ 3 callersClassTAEHV
examples/WanVSR/utils/TCDecoder.py:170
↓ 3 callersClassTGrow
examples/WanVSR/utils/TCDecoder.py:63
↓ 3 callersClassTableManager
diffsynth/extensions/FastBlend/runners/fast.py:8
↓ 3 callersClassTileWorker2Dto3D
Process 3D tensors, but only enable TileWorker on 2D.
diffsynth/models/tiler.py:164
↓ 3 callersClassUpsample3D
diffsynth/models/cog_vae.py:57
↓ 2 callersClassAttentionBlock
diffsynth/models/wan_video_image_encoder.py:53
↓ 2 callersClassAttentionModule
diffsynth/models/wan_video_dit.py:290
↓ 2 callersClassAttnBlock
diffsynth/models/stepvideo_vae.py:466
↓ 2 callersClassAugmentationCfg
diffsynth/extensions/ImageQualityMetric/open_clip/transform.py:16
↓ 2 callersClassBertAttention
diffsynth/extensions/ImageQualityMetric/BLIP/med.py:234
↓ 2 callersClassBertModel
The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of cross-attention is added between
diffsynth/extensions/ImageQualityMetric/BLIP/med.py:563
↓ 2 callersClassBottleneck
diffsynth/extensions/ImageQualityMetric/open_clip/modified_resnet.py:10
↓ 2 callersClassCLIP
diffsynth/extensions/ImageQualityMetric/open_clip/model.py:176
↓ 2 callersClassChannelDuplicatingPixelUnshuffleUpSampleLayer3D
diffsynth/models/stepvideo_vae.py:262
↓ 2 callersClassChatGLMModel
diffsynth/models/kolors_text_encoder.py:991
↓ 2 callersClassControlNetConditioningLayer
diffsynth/models/sd_controlnet.py:6
↓ 2 callersClassFluxJointTransformerBlock
diffsynth/models/flux_dit.py:109
↓ 2 callersClassFluxSingleTransformerBlock
diffsynth/models/flux_dit.py:206
↓ 2 callersClassHuggingfaceTokenizer
diffsynth/prompters/wan_prompter.py:36
↓ 2 callersClassHunyuanDiTBlock
diffsynth/models/hunyuan_dit.py:87
↓ 2 callersClassHunyuanDiTRotaryEmbedding
diffsynth/models/hunyuan_dit.py:7
↓ 2 callersClassInvalidScoreLogitsProcessor
diffsynth/models/kolors_text_encoder.py:311
↓ 2 callersClassIpAdapterImageProjModel
diffsynth/models/sdxl_ipadapter.py:17
↓ 2 callersClassIpAdapterModule
diffsynth/models/flux_ipadapter.py:27
↓ 2 callersClassJointTransformerBlock
diffsynth/models/sd3_dit.py:243
↓ 2 callersClassKeyFrameMatcher
diffsynth/extensions/FastBlend/api.py:92
↓ 2 callersClassKolorsPrompter
diffsynth/prompters/kolors_prompter.py:307
↓ 2 callersClassMMDoubleStreamBlockComponent
diffsynth/models/hunyuan_video_dit.py:403
↓ 2 callersClassMlp
MLP as used in Vision Transformer, MLP-Mixer and related networks
diffsynth/extensions/ImageQualityMetric/BLIP/vit.py:19
↓ 2 callersClassMultimodalCfg
diffsynth/extensions/ImageQualityMetric/open_clip/coca_model.py:45
↓ 2 callersClassPatchEmbed
diffsynth/models/sd3_dit.py:28
↓ 2 callersClassPatchEmbedMR
2D Image to Patch Embedding
diffsynth/models/omnigen.py:307
next →1–100 of 521, ranked by callers