MCPcopy Create free account

hub / github.com/amap-cvlab/ABot-PhysWorld / types & classes

Types & classes770 in github.com/amap-cvlab/ABot-PhysWorld

⨍ Functions 2,967◇ Types & classes 770↳ Endpoints 1
↓ 141 callersClassResnetBlock
inference/diffsynth/models/sd_unet.py:94
↓ 105 callersClassPushBlock
inference/diffsynth/models/sd_unet.py:211
↓ 55 callersClassAttentionBlock
inference/diffsynth/models/sd_unet.py:126
↓ 38 callersClassPopMixBlock
inference/diffsynth/models/svd_unet.py:224
↓ 36 callersClassTemporalBlock
inference/diffsynth/models/sd_motion.py:52
↓ 33 callersClassPopBlock
inference/diffsynth/models/sd_unet.py:220
↓ 32 callersClassResnet3DBlock
inference/diffsynth/models/cog_vae.py:128
↓ 22 callersClassCausalConv3d
Causal 3d convolusion.
inference/diffsynth/models/wan_video_vae.py:33
↓ 22 callersClassTemporalResnetBlock
inference/diffsynth/models/svd_unet.py:6
↓ 20 callersClassModelConfig
inference/diffsynth/utils/__init__.py:159
↓ 19 callersClassDownSampler
inference/diffsynth/models/sd_unet.py:70
↓ 17 callersClassUpSampler
inference/diffsynth/models/sd_unet.py:83
↓ 16 callersClassRMSNorm
inference/diffsynth/models/sd3_dit.py:8
↓ 16 callersClassTemporalAttentionBlock
inference/diffsynth/models/svd_unet.py:145
↓ 14 callersClassTemporalResnetBlock
inference/diffsynth/models/svd_vae_decoder.py:45
↓ 12 callersClassAttention
inference/diffsynth/models/attention.py:15
↓ 12 callersClassResidualBlock
inference/diffsynth/models/wan_video_vae.py:267
↓ 11 callersClassFlowMatchScheduler
inference/diffsynth/schedulers/flow_match.py:5
↓ 11 callersClassQwenImageCausalConv3d
r""" A custom 3D causal convolution layer with feature caching support. This layer extends the standard Conv3D layer by ensuring causality in
inference/diffsynth/models/qwen_image_vae.py:8
↓ 10 callersClassAdaLayerNorm
inference/diffsynth/models/sd3_dit.py:85
↓ 10 callersClassEnhancedDDIMScheduler
inference/diffsynth/schedulers/ddim.py:4
↓ 10 callersClassTimestepEmbeddings
inference/diffsynth/models/sd3_dit.py:67
↓ 9 callersClassPyramidPatchMatcher
inference/diffsynth/extensions/FastBlend/patch_match.py:206
↓ 9 callersClassTileWorker
inference/diffsynth/models/tiler.py:5
↓ 9 callersClassTimesteps
inference/diffsynth/models/sd_unet.py:6
↓ 8 callersClassCausalConvChannelLast
inference/diffsynth/models/stepvideo_vae.py:414
↓ 8 callersClassRMSNorm
inference/diffsynth/models/flux_dit.py:518
↓ 7 callersClassCachedConv3d
inference/diffsynth/models/cog_vae.py:169
↓ 7 callersClassImageCropAndResize
inference/diffsynth/trainers/unified_dataset.py:73
↓ 7 callersClassModelManager
inference/diffsynth/models/model_manager.py:316
↓ 7 callersClassRMS_norm
inference/diffsynth/models/wan_video_vae.py:55
↓ 7 callersClassToAbsolutePath
inference/diffsynth/trainers/unified_dataset.py:300
↓ 6 callersClassAttentionBlock
Causal self-attention with a single head.
inference/diffsynth/models/wan_video_vae.py:304
↓ 6 callersClassBaseGroupNorm
inference/diffsynth/models/stepvideo_vae.py:21
↓ 6 callersClassCausalConv
inference/diffsynth/models/stepvideo_vae.py:226
↓ 6 callersClassCausalConv3d
inference/diffsynth/models/hunyuan_video_vae_decoder.py:10
↓ 6 callersClassCausalConvAfterNorm
inference/diffsynth/models/stepvideo_vae.py:438
↓ 6 callersClassRMSNorm
inference/diffsynth/models/hunyuan_video_dit.py:732
↓ 6 callersClassResnet3DBlock
inference/diffsynth/models/stepvideo_vae.py:498
↓ 5 callersClassCLIPEncoderLayer
inference/diffsynth/models/sd_text_encoder.py:5
↓ 5 callersClassLayerNorm
inference/diffsynth/models/wan_video_image_encoder.py:228
↓ 5 callersClassPipelineUnitRunner
inference/diffsynth/utils/__init__.py:247
↓ 5 callersClassQwen2RMSNorm
inference/diffsynth/models/nexus_gen_projector.py:198
↓ 5 callersClassQwenImageRMS_norm
r""" A custom RMS normalization layer. Args: dim (int): The number of dimensions to normalize over. channel_first (bool, opti
inference/diffsynth/models/qwen_image_vae.py:54
↓ 5 callersClassRMSNorm
inference/diffsynth/models/wan_video_dit.py:100
↓ 4 callersClassAnnotator
inference/diffsynth/controlnets/processors.py:8
↓ 4 callersClassCausalConv1d
inference/diffsynth/models/wan_video_dit_s2v.py:86
↓ 4 callersClassControlNetUnit
inference/diffsynth/controlnets/controlnet_unit.py:14
↓ 4 callersClassConvLayer
inference/diffsynth/models/wan_video_animate_adapter.py:452
↓ 4 callersClassDataProcessingPipeline
inference/diffsynth/trainers/unified_dataset.py:7
↓ 4 callersClassFP32_Layernorm
inference/diffsynth/models/hunyuan_dit.py:55
↓ 4 callersClassFP32_SiLU
inference/diffsynth/models/hunyuan_dit.py:61
↓ 4 callersClassGEGLU
inference/diffsynth/models/sd_unet.py:20
↓ 4 callersClassGeneralLoRALoader
inference/diffsynth/lora/__init__.py:5
↓ 4 callersClassIFBlock
inference/diffsynth/extensions/RIFE/__init__.py:34
↓ 4 callersClassJointAttention
inference/diffsynth/models/sd3_dit.py:112
↓ 4 callersClassLayerNorm_FP32
inference/diffsynth/models/longcat_video_dit.py:327
↓ 4 callersClassLayerScale
inference/diffsynth/extensions/ImageQualityMetric/open_clip/transformer.py:37
↓ 4 callersClassQuantizedLinear
inference/diffsynth/models/kolors_text_encoder.py:158
↓ 4 callersClassQwenImageResidualBlock
r""" A custom residual block module. Args: in_dim (int): Number of input channels. out_dim (int): Number of output channels.
inference/diffsynth/models/qwen_image_vae.py:81
↓ 4 callersClassRMSNorm
inference/diffsynth/models/stepvideo_dit.py:20
↓ 4 callersClassRMSNorm_FP32
inference/diffsynth/models/longcat_video_dit.py:15
↓ 4 callersClassResnetBlockCausal3D
inference/diffsynth/models/hunyuan_video_vae_decoder.py:64
↓ 4 callersClassTimestepEmbedding
inference/diffsynth/models/stepvideo_dit.py:163
↓ 4 callersClassUpsample
inference/diffsynth/models/wan_video_vae.py:73
↓ 4 callersClassVAEAttentionBlock
inference/diffsynth/models/sd_vae_decoder.py:7
↓ 4 callersClassVideoData
inference/diffsynth/extensions/FastBlend/data.py:96
↓ 4 callersClassWanPrompter
inference/diffsynth/prompters/wan_prompter.py:84
↓ 3 callersClassCLIPTextCfg
inference/diffsynth/extensions/ImageQualityMetric/open_clip/model.py:49
↓ 3 callersClassCLIPVisionCfg
inference/diffsynth/extensions/ImageQualityMetric/open_clip/model.py:24
↓ 3 callersClassCausalConv1d
inference/diffsynth/models/wan_video_animate_adapter.py:50
↓ 3 callersClassCogAdaLayerNorm
inference/diffsynth/models/cog_dit.py:23
↓ 3 callersClassCogVideoXSpatialNorm3D
inference/diffsynth/models/cog_vae.py:103
↓ 3 callersClassDownsample3D
inference/diffsynth/models/cog_vae.py:7
↓ 3 callersClassEqualLinear
inference/diffsynth/models/wan_video_animate_adapter.py:422
↓ 3 callersClassFluxLoRALoader
inference/diffsynth/lora/flux_lora.py:8
↓ 3 callersClassHFTokenizer
HuggingFace tokenizer wrapper
inference/diffsynth/extensions/ImageQualityMetric/open_clip/tokenizer.py:188
↓ 3 callersClassLayerNorm
inference/diffsynth/extensions/ImageQualityMetric/trainer/models/cross_modeling.py:18
↓ 3 callersClassLoadImage
inference/diffsynth/trainers/unified_dataset.py:62
↓ 3 callersClassLoadVideo
inference/diffsynth/trainers/unified_dataset.py:117
↓ 3 callersClassModulateDiT
inference/diffsynth/models/hunyuan_video_dit.py:275
↓ 3 callersClassMultiControlNetManager
inference/diffsynth/controlnets/controlnet_unit.py:21
↓ 3 callersClassResidualDenseBlock
inference/diffsynth/extensions/ESRGAN/__init__.py:7
↓ 3 callersClassT5LayerNorm
inference/diffsynth/models/wan_video_text_encoder.py:22
↓ 3 callersClassTableManager
inference/diffsynth/extensions/FastBlend/runners/fast.py:8
↓ 3 callersClassTemporalTimesteps
inference/diffsynth/models/svd_unet.py:87
↓ 3 callersClassTileWorker2Dto3D
Process 3D tensors, but only enable TileWorker on 2D.
inference/diffsynth/models/tiler.py:164
↓ 3 callersClassUpsample3D
inference/diffsynth/models/cog_vae.py:57
↓ 2 callersClassAttentionBlock
inference/diffsynth/models/wan_video_image_encoder.py:53
↓ 2 callersClassAttentionModule
inference/diffsynth/models/wan_video_dit.py:114
↓ 2 callersClassAttnBlock
inference/diffsynth/models/stepvideo_vae.py:466
↓ 2 callersClassAugmentationCfg
inference/diffsynth/extensions/ImageQualityMetric/open_clip/transform.py:16
↓ 2 callersClassBertAttention
inference/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
inference/diffsynth/extensions/ImageQualityMetric/BLIP/med.py:563
↓ 2 callersClassBottleneck
inference/diffsynth/extensions/ImageQualityMetric/open_clip/modified_resnet.py:10
↓ 2 callersClassCLIP
inference/diffsynth/extensions/ImageQualityMetric/open_clip/model.py:176
↓ 2 callersClassChannelDuplicatingPixelUnshuffleUpSampleLayer3D
inference/diffsynth/models/stepvideo_vae.py:262
↓ 2 callersClassChatGLMModel
inference/diffsynth/models/kolors_text_encoder.py:991
↓ 2 callersClassControlNetConditioningLayer
inference/diffsynth/models/sd_controlnet.py:6
↓ 2 callersClassCrossAttention
inference/diffsynth/models/wan_video_dit.py:150
next →1–100 of 770, ranked by callers