Wan2.2-Animate in ComfyUI: Create AI Character Animations Locally

About This Workflow

Animate a single character image by transferring facial expressions and body movements from a reference video.

Replace a person in a video with your own character while keeping the original lighting, colors, and background intact.

Create smooth, realistic AI animations suitable for storytelling, short films, social media, or concept videos.

Control animation quality by adjusting frames, frame rate, resolution, masking, and LoRA strength inside ComfyUI.

Run the entire animation workflow locally on your GPU, with no cloud usage, no API limits, and full creative control.

Required Models

Model links

Model links:

https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main/Wan22Animate

GGUF Model links:

https://huggingface.co/QuantStack/Wan2.2-Animate-14B-GGUF/tree/main

LoRA:

https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v

https://huggingface.co/Kijai/WanVideo_comfy/blob/main/WanAnimate_relight_lora_fp16.safetensors

Text encoder:

https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-bf16.safetensors

VAE:

https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VAE_bf16.safetensors

ComfyUI/
└── models/
    ├── diffusion_models/
    │   └── Wan2_2-Animate-14B_fp8_e4m3fn_scaled_KJ.safetensors (or e5m2 or GGUF version)
    ├── text_encoders/
    │   └── umt5-xxl-enc-bf16.safetensors
    ├── vae/
    │   └── Wan2_1_VAE_bf16.safetensors
    └── lora/
        ├── WanAnimate_relight_lora_fp16.safetensors
        └── lightx2v_I2V_14B_480p_cfg_step_distill_rank256_bf16.safetensors

Workflow Graph