Wan2.1 Uni3C Image to Video
Image to Video
Uni3C
Wan
0
692
Nodes & Models
WanVideoTorchCompileSettings
WanVideoBlockSwap
WanVideoUni3C_ControlnetLoader
Wan21_Uni3C_controlnet_fp16.safetensors
WanVideoContextOptions
WanVideoVAELoader
Wan2_1_VAE_bf16.safetensors
WanVideoLoraSelect
Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32.safetensors
WanVideoTextEncode
WanVideoEncode
WanVideoClipVisionEncode
WanVideoUni3C_embeds
WanVideoImageToVideoEncode
WanVideoSampler
WanVideoDecode
WanVideoUni3C_ControlnetLoader
Wan21_Uni3C_controlnet_fp16.safetensors
WanVideoUni3C_embeds
WanVideoUni3C_ControlnetLoader
Wan21_Uni3C_controlnet_fp16.safetensors
WanVideoUni3C_embeds
INTConstant
INTConstant
GetImageSizeAndCount
ImageResizeKJv2
AddLabel
ImageConcanate
GetImageSizeAndCount
ImageResizeKJv2
AddLabel
ImageConcanate
VHS_LoadVideo
VHS_VideoCombine
WanVideoEncode
RIFE VFI
rife47.pth
Overview
Uni3C is a unified 3D-enhanced framework integrated into ComfyUI that enables precise, simultaneous control over both camera motion and human animation within video generation workflows. By leveraging a lightweight plug-and-play control module, Uni3C extracts and transfers motion—such as camera movements and character actions—from reference videos directly onto new scenes or images, eliminating the need for complex manual rigging or joint annotation.
Key Inputs
Image Reference - Load an Image you want to turn into a video and follows the reference video.
Video Reference - Load a video which shows a movement or direction.
Read more
N


