Luma Reframe Video

Luma Reframe Video seamlessly transforms video aspect ratios, perfect for adapting content across various social media platforms.

Platform: Replicate

Video ReframingAspect Ratio ConversionSocial Media AdaptationVideo Processing

674 runs

0.06 per second of output video

Commercial

🚀Function Overview

A model that changes video aspect ratios using guided prompts and precise positioning controls, outputting 720p videos suitable for social media platforms.

Key Features

Reframes videos to target aspect ratios (e.g., 16:9 to 9:16)
Guided content repositioning via prompts
Pixel-precise control over crop bounds and grid positioning
720p output resolution
Supports videos up to 30 seconds and 100MB

Use Cases

•Adapting landscape videos for TikTok/Reels/Shorts
•Formatting videos for square content displays
•Professional video repurposing for multi-platform distribution
•Content repositioning with AI-guided framing

⚙️Input Parameters

video_url

string

URL of the video to reframe. Maximum video size is 100mb. Maximum video duration is 30 seconds.

aspect_ratio

string

Aspect ratio of the output

prompt

string

A prompt to guide the reframing generation

grid_position_x

integer

The x position of the input in the grid, in pixels. Controls horizontal positioning of the source within the target output dimensions.

grid_position_y

integer

The y position of the input in the grid, in pixels. Controls vertical positioning of the source within the target output dimensions.

x_start

integer

The x start of the crop bounds, in pixels. Defines the left boundary where your source will be placed in the output frame. The distance between x_start and x_end determines the resized width of your content.

x_end

integer

The x end of the crop bounds, in pixels. Defines the right boundary where your source will be placed in the output frame. The distance between x_start and x_end determines the resized width of your content.

y_start

integer

The y start of the crop bounds, in pixels. Defines the top boundary where your source will be placed in the output frame. The distance between y_start and y_end determines the resized height of your content.

y_end

integer

The y end of the crop bounds, in pixels. Defines the bottom boundary where your source will be placed in the output frame. The distance between y_start and y_end determines the resized height of your content.

💡Usage Examples

Example 1

Input Parameters

{
  "prompt": "A woman is standing in a room as part of a podcast show",
  "video_url": "https://replicate.delivery/pbxt/NAOh1kWFGdaSfwvwYzE7eIKypI9JB5rBs0kAb1HVeGDmmNtg/A_podcast_show_202506111026_uikpa.mp4",
  "aspect_ratio": "9:16"
}

Output Results

https://replicate.delivery/xezq/KSUvcJrFAHJ0IhsvD8eew2AvOesvFl85CqLfzjaMiaBfMfbNF/tmp5e959bwx.mp4

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type
Run Count: 674
Commercial Use: Supported
Pricing: 0.06 per second of output video
Platform: Replicate

Related Keywords

Video ReframingAspect Ratio ConversionSocial Media AdaptationContent RepositioningMulti-platform DistributionGuided PromptsPixel-precise Control

Related Models

Frames to Video Merger

Convert a set of image frames (JPG or PNG) into a high-quality MP4 video. Automatically handles sorting and frame order for smooth playback.

twha Video Generation Model

A model for generating videos from text prompts and starting images.

Leonardo AI Motion 2.0

Create 5s 480p videos from a text prompt