Skip to main content
Wan-Move is a motion-controllable video generation framework developed by Alibabaโ€™s Tongyi Lab. It enables users to control object motion in generated videos by specifying point trajectories on the input image, making image-to-video generation more precise and controllable. Key Features:
  • High-Quality 5s 480p Motion Control: Generates 5-second, 480p videos with fine-grained motion controllability
  • Latent Trajectory Guidance: Represents motion conditions by propagating first frame features along trajectories
  • Fine-grained Point-level Control: Object motions are represented with dense point trajectories, enabling precise region-level control
  • No Architecture Changes: Seamlessly integrates into Wan-I2V-14B without extra motion modules
Related Links:

โ€‹
Wan-Move image-to-video workflow

Preview the workflow output: Wan-Move preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search โ€œWan-Move Motion-Controlโ€ in Template Library
Input materials Upload this file to the matching LoadImage node:

snowboard_rush.png

LoadImage node ยท snowboard_rush.png
snowboard_rush.png
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you canโ€™t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

Checkpoint: Wan21-WanMove

Place in ComfyUI/models/diffusion_models/

LoRA: LightX2V Distilled

Place in ComfyUI/models/loras/

Text Encoder: umt5

Place in ComfyUI/models/text_encoders/

CLIP Vision: clip_vision_h

Place in ComfyUI/models/clip_vision/

VAE: wan_2.1_vae

Place in ComfyUI/models/vae/
Model Storage Location