The formats differ on three axes at once: the shape of the frame, the length that is rewarded, and where the interface covers the picture. A widescreen edit posted vertically is not merely letterboxed — its subject is smaller, its on-screen text is unreadable and the part of the frame the viewer's thumb sits over was never considered.
Reframing is therefore not a crop. Something has to decide where the subject is in each shot and keep it in the new frame, which is a re-render rather than an export setting. Where the source was generated in the first place, the cheaper move is usually to go back to the script or the scenes and render the new ratio from there, because nothing has to be recovered from pixels that were thrown away.
Language is the second axis, and it is the one most teams leave on the table. A finished video dubbed into another language is a genuinely new piece of distribution for a fraction of the work that produced the original — and with lip-synced dubbing, one that does not obviously read as a translation.
In practice
- Produce vertical first when vertical is where the audience is; upscaling attention from a widescreen edit is the harder direction.
- Re-render from the script rather than cropping the export whenever the source was generated.
- Re-check caption placement after every reframe — the safe area moves with the frame.
Models that read video in
Models that accept footage as an input rather than only emitting it. 26 of the 296 models in the Versely catalog qualify.
| Model | Provider | Type |
|---|---|---|
| Seedance 2.0 | ByteDance | Video |
| Flux 3 Extend Video | Black Forest Labs | Video |
| Gemini Omni Flash Edit | Video | |
| Happy Horse 1.0 Video Edit | Alibaba | Video |
| Wan 2.7 Reference to Video | Wan | Video |
| Wan 2.7 Video Edit | Wan | Video |
| Kling Video V3 Pro Motion Control | Kling | Video |
| Kling Video V3 Standard Motion Control | Kling | Video |
Browse all 11 spec pages for full settings, resolutions and credit costs.
The mistake to avoid
Repurposing by re-uploading. The same file on four platforms is one piece of content that underperforms on three of them, and the platforms are increasingly good at spotting it.
Where you will run into it
- Change a Video's Aspect Ratio — One clip. Any frame.
- Make a Video Vertical — Landscape in. Full-screen mobile out.
- Convert a Video to Shorts — Find the best 30 seconds. Reformat it. Post it.
- Convert a Vertical Video to Horizontal — Phone-shot footage, made presentation-ready.
- AI Dubbing Tool — One approved video. Several markets.
- AI Social Media Video Generator — Made for the feed it posts to, then posted to it.
- AI Reel Maker — Hook, beats, captions, posted.
Related terms
Aspect ratio
Aspect ratio is the proportion between an output's width and its height, written as two numbers — 16:9 for landscape, 9:16 for a full phone screen.
Content velocity
Content velocity is how much finished, publishable work actually ships per week — the throughput of the pipeline rather than the quality of any single piece.
AI dubbing
AI dubbing replaces a video's spoken audio with another language, usually keeping the original speaker's voice and optionally re-syncing their mouth.
Retention curve
A retention curve shows how many of the people who started a video are still watching at each second of it, and watch time is the area under that curve.
Brand kit
A brand kit is the saved set of colours, fonts, logo, product images, tone of voice and default frame shape that generations are expected to obey without being reminded.
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.