Vertical Video Reframe

Vertical video reframe
smart 9:16 crop with subject tracking

Reframe horizontal video to vertical 9:16 automatically with subject-aware cropping. EditAssist tracks faces and action to keep the important content in frame, then exports to TikTok, Reels, Shorts, and Stories specs.

01

Workflow

Select your horizontal sequence and ask for a vertical recut. The agent analyses subject movement, face positions, and action across every frame, then generates a 9:16 crop that tracks the important content. It handles talking heads, moving subjects, and multi-person shots with intelligent framing.

Export to all vertical specs at once: 9:16 for TikTok, Reels, and Shorts; 4:5 for Instagram feed; 1:1 for square formats. The agent can batch-reframe an entire series, maintaining consistent framing rules across episodes. All processing is local.

02

Prompts

  • Create a vertical 9:16 recut of this horizontal sequence.

  • Reframe the widescreen music video into 9:16, 1:1, and 4:5 for every platform in one go.

  • Split the long-form cut into social deliverables: 16:9, 9:16, and 1:1 with safe-area reframing.

  • Create a 4:5 vertical version of the trailer for Instagram feed with blurred pillarboxing.

  • Reframe the 16:9 master for Instagram Reels: vertical crop with subject tracking.

  • Build a vertical edit of the dance sequence with beat-matched cuts for Instagram Reels.

  • Export separate 16x9 and 9x16 versions for YouTube and TikTok.

  • Repurpose the hero video into 4 platform-specific aspect ratios.

03

Features

Subject-aware crop

Tracks faces and action across frames so important content stays in the 9:16 safe area, even with moving subjects.

Multi-format batch export

Reframe to 9:16, 1:1, 4:5, and 16:9 in a single command, with platform-specific safe-area margins.

Consistent series framing

Apply the same reframing rules across an entire series for consistent vertical presentation.

Local GPU processing

All analysis and rendering runs on your own machine. No upload, no queue, no cloud dependency.

04

Local-first

All transcription, vision analysis, semantic search, and clustering run on your own GPU. Nothing about your footage is uploaded. The only data that leaves is the text of your conversation with the agent. It's free to download, local models are free, and a new account starts with £15 of credit and no card. For long-running cloud work, pay as you go, or choose £20/mo Starter or £100/mo Pro.

05

Getting started

  1. 01Download EditAssist for macOS or Windows and create an account. You get £15 credit and no card is needed.
  2. 02Ingest your footage. The agent transcribes, indexes, and clusters automatically.
  3. 03Describe what you want in plain English and let the agent build the cut.
  4. 04Review, refine with conversational commands, and export to your delivery spec.

More tools: YouTube Shorts generator, Auto clip generator, AI B-roll finder. Or see everything EditAssist connects to.