ActionHug is a motion-focused LoRA designed for WAN 2.2 and I2V pipelines, adding a smooth, natural “approach and back-hug” action to any character without changing their identity or body proportions.
Trained exclusively on AI-generated clips, this LoRA generalizes well across different scenes, outfits, and poses.
Trigger words
You should use actionhug to trigger the image generation.
