> For the complete documentation index, see [llms.txt](https://docs.pletor.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.pletor.ai/models/video-models/ltx-2.5-reframe.md).

# LTX 2.5 Reframe

A video reframing model by Lightricks: changes a video's aspect ratio without cropping the subject.

## TL;DR

The fastest way to turn one master video into vertical, square and feed formats. It recenters your footage and generates the newly exposed areas, so the result looks shot natively in the target format.

### Strengths for marketers

* **No lost subject**: the whole original frame is kept; only the new edges are generated.
* **Five social formats**: 9:16, 4:5, 1:1, 5:4, 16:9.
* **No prompt needed**.
* **Up to 1080p**.

### Ideal use cases

* **Social repurposing**: one 16:9 ad into 9:16, 4:5 and 1:1 placements.
* **Vertical video** from TV or YouTube cuts.
* **Batch format adaptation** across a campaign's cuts.

### Weaknesses

* No control over what fills the new area; for a guided result, use [Runway Aleph 2.0](https://docs.pletor.ai/models/video-models/runway-aleph.md)'s format expansion with a prompt.
* The source is always centered; placement can't be adjusted.
* The bigger the ratio change, the more is generated and the more to review.

***

## How to use effectively

Use the **Reframe video** node: connect a video, choose the target aspect ratio and resolution. Reframe last, after edits and upscaling, so every format comes from the same master.

***

## Model parameters

* **Output**: 720p or 1080p (default 1080p); 9:16 (default), 4:5, 1:1, 5:4, 16:9; same duration as the source.
