SteadyDancer
dancing
0
199
Nodes & Models
WanVideoVAELoader
Wan2_1_VAE_bf16.safetensors
GetNode
WanVideoContextOptions
WanVideoScheduler
WanVideoTextEncodeCached
umt5-xxl-enc-bf16.safetensors
WanVideoModelLoader
Wan21_SteadyDancer_fp8_e4m3fn_scaled_KJ.safetensors
WanVideoLoraSelect
lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
WanVideoTorchCompileSettings
LoadImage
WanVideoBlockSwap
Note
SetNode
ImageConcatMulti
WanVideoSetBlockSwap
ImageResizeKJv2
GetImageSizeAndCount
WanVideoSetLoRAs
WanVideoClipVisionEncode
WanVideoImageToVideoEncode
WanVideoEncode
GetImageRangeFromBatch
WanVideoAddSteadyDancerEmbeds
WanVideoSamplerSettings
WanVideoSamplerFromSettings
WanVideoDecode
OnnxDetectionModelLoader
PoseAndFaceDetection
DrawViTPose
VHS_LoadVideo
VHS_VideoCombine
VHS_LoadVideo
VHS_VideoCombine
easy showAnything
This repository is the official implementation of paper "SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation". SteadyDancer is a strong animation framework based on Image-to-Video paradigm, ensuring robust first-frame preservation. In contrast to prior Reference-to-Video approaches that often suffer from identity drift due to spatio-temporal misalignments common in real-world applications, SteadyDancer generates high-fidelity and temporally coherent human animations, outperforming existing methods in visual quality and control while requiring significantly fewer training resources.
Read more
N