fal-ai/wan-move

Use Wan-Move to generate videos with controlled the motion using trajectories

Inference

Commercial use

This endpoint is deprecated

This model is no longer supported.

Schema

LLMs

Playground API

Input

Image Url*

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif

Prompt*

In a boxing gym, the camera captures a half-body view of a single man practicing shadow boxing inside the ring. The camera sways slightly, emphasizing movement and intensity. He wears black boxing gloves, black shorts, and boxing shoes. With no opponent present, he throws a controlled straight punch into the air, his lead arm fully extended while the other hand stays tight near his face in a defensive guard. His body rotates subtly through the hips and shoulders, and his feet shift lightly across the mat to maintain balance and rhythm. Sweat highlights his muscular form as he focuses forward, fully immersed in his training. The background features blurred gym equipment and hanging heavy bags, reinforcing the sense of motion and concentration.

Type # to reference inputs.

Trajectories*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "content_type": "video/mp4",
    "file_name": "output.mp4",
    "num_frames": 81,
    "width": 624,
    "height": 624,
    "fps": 16,
    "duration": 5.0626,
    "url": "https://storage.googleapis.com/falserverless/example_outputs/wan_move/output.mp4"
  }
}

Your request will cost $0.2 per video.

fal-ai/wan-move

This endpoint is deprecated

Input

Result

What would you like to do next?

Logs