Skip to main content
Decart offers AI models for video editing, motion control, and image editing. Transform existing media with intelligent edits while preserving important details like motion, temporal consistency, identity, and structure.

Available models

Video Editing

Transform and edit existing videos with Lucy Edit 2

Motion Control

Control object motion with precise trajectory paths

Image Editing

Transform and edit existing images with LucyEdit

Quick comparison

FeatureVideo EditingMotion ControlImage Editing
ModelsLucy Edit 2, Lucy Edit v1 (Legacy)Lucy MotionLucyEdit
Input typesVideo + text prompt, video + reference image, or bothImage + trajectory coordinatesImage + text prompt
Resolution720p720p720p
Best forEditing existing videosTrajectory-based animationEditing existing images
StrengthsMotion preservation, temporal consistencyPrecise path control, keyframe-based movementIdentity preservation, structure retention

Model capabilities

Video Editing (Lucy Edit 2)

  • Flexible inputs: Use a text prompt, a reference image, or both together
  • Reference image mode: Transform video to match a reference image without needing a prompt
  • Combined mode: Pair a reference image with a text prompt for maximum control
  • Excels at: Clothing changes, character/object replacement, style transfers, background replacement
  • Preserves: Original motion patterns, temporal consistency, scene structure
  • Unlimited duration — no 5-second clip limit
  • Best results with 20-40 word prompts focusing on specific changes
Legacy model Lucy Edit v1 (lucy-pro-v2v) is still available but limited to 5-second clips. Use Lucy Edit 2 (lucy-2-v2v) for new projects.

Motion Control (Lucy Motion)

  • Trajectory-based Animation: Control object motion with precise coordinate paths
  • Define keyframes with exact x, y positions for predictable movement
  • No prompt needed — motion is defined by your trajectory coordinates

Image Editing (LucyEdit)

  • Excels at: Clothing changes, character/object replacement
  • Good for: Color changes, adding accessories, background transformations
  • Preserves: Core structure, pose, identity
  • Best results with 20-30 word prompts focusing on specific changes

API endpoints

Video

Image

Next steps

Go to Platform

Test all models interactively

API Reference

Complete documentation for all endpoints