[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [LTX 2.3 Reframe](https://spiral.ai/integrations/instinct/ltx-2-3-reframe)

# How to Use LTX 2.3 Reframe in Instinct

LTX 2.3 Reframe adapts existing footage to a different screen shape by generating the missing areas around it. Use it to repurpose a finished clip while keeping content that a crop would remove.

|  |  |
| --- | --- |
| Model | LTX 2.3 Reframe |
| Available through | fal |
| Category | Video |
| Price | Up to $15.60 per run at the default inputs for 60 seconds of input. `resolution`: 720p $7.80, 1080p (default) $15.60. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with LTX 2.3 Reframe in Instinct

- Each morning, use LTX 2.3 Reframe to make vertical 1080p copies of newly approved interview excerpts. Process only clips within 60 seconds and 1,800 frames, and collect the results for review.
- Every Monday, use LTX 2.3 Reframe to create square and portrait 4:5 versions of approved product clips at 1080p. Skip clips over 60 seconds or 1,800 frames.
- At the end of each day, use LTX 2.3 Reframe to make landscape 720p review copies of approved portrait event clips under 20 seconds. Include a reminder to inspect the generated side areas.
- Every Friday, use LTX 2.3 Reframe to prepare vertical and square 1080p copies of the week's approved 15-second ads. Pair each result with its source for review.
- Each afternoon, use LTX 2.3 Reframe to create portrait 4:5 copies of newly approved training excerpts at 1080p. Check the 60-second and 1,800-frame limits before processing.

## How to set up LTX 2.3 Reframe in Instinct

Pick the way that suits you. Each takes about two minutes.

### Use the Spiral skill

1. **Send Instinct this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use Spiral's MCP server

1. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run LTX 2.3 Reframe**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/ltx-2.3/reframe",
    "input": {
      "video_url": "https://storage.googleapis.com/falserverless/example_outputs/ltxv-2-t2v-output.mp4"
    }
  }'
```

Then paste one of the prompts above: Instinct finds LTX 2.3 Reframe on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/instinct

## LTX 2.3 Reframe tools and prices

- [Ltx 2.3 · Reframe](https://spiral.ai/tools/fal/fal-ai/ltx-2.3/reframe) (fal): `resolution`: 720p $0.13, 1080p (default) $0.26 per second.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| aspect_ratio | 1:1, 4:5, 5:4, 9:16, 16:9 | 16:9 | The target aspect ratio to reframe the video to. |
| resolution | 720p, 1080p | 1080p | The target output resolution tier. Combined with the aspect ratio to determine the output size. |

## What can you do with LTX 2.3 Reframe in Instinct?

Prepare different screen shapes from recurring batches of approved footage with LTX 2.3 Reframe. A scheduled agent can check clip lengths and frame counts, create the requested compositions, and collect results for review.

### Vertical interview excerpts

Use LTX 2.3 Reframe to adapt a landscape interview excerpt for a vertical placement. Review the expanded background around the speaker before delivery.

### Square product demonstrations

Turn an existing product demonstration into a square feed clip with LTX 2.3 Reframe. Compare it with a crop to check whether the product and demonstrator remain easier to see.

### Ad placement adaptations

Prepare portrait, square, and landscape versions of a finished short ad with LTX 2.3 Reframe. Review each composition separately before adding placement-specific text.

### Widescreen versions of portrait footage

Expand a portrait event excerpt into a landscape composition with LTX 2.3 Reframe. Inspect the generated side areas for consistency with the visible venue.

### Website video adaptations

Use LTX 2.3 Reframe to adapt a short existing brand video for a landscape website placement and a portrait mobile placement. Preview both in the intended layouts.

### Training video excerpts

Adapt a short instructor demonstration to a different screen shape with LTX 2.3 Reframe. Check hands, tools, and the generated surroundings before including it in a lesson.

### Music performance promos

Create differently shaped promotional excerpts from an existing performance video with LTX 2.3 Reframe. Review the added stage areas and listen through the result.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## LTX 2.3 Reframe in other agents

- [Amp](https://spiral.ai/integrations/amp/ltx-2-3-reframe)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/ltx-2-3-reframe)
- [Claude](https://spiral.ai/integrations/claude-desktop/ltx-2-3-reframe)
- [Claude Code](https://spiral.ai/integrations/claude-code/ltx-2-3-reframe)
- [Cline](https://spiral.ai/integrations/cline/ltx-2-3-reframe)
- [Codex](https://spiral.ai/integrations/codex/ltx-2-3-reframe)
- [Cursor](https://spiral.ai/integrations/cursor/ltx-2-3-reframe)
- [Devin](https://spiral.ai/integrations/devin/ltx-2-3-reframe)
- [dots](https://spiral.ai/integrations/dots/ltx-2-3-reframe)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/ltx-2-3-reframe)
- [Gemini](https://spiral.ai/integrations/gemini/ltx-2-3-reframe)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/ltx-2-3-reframe)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/ltx-2-3-reframe)
- [goose](https://spiral.ai/integrations/goose/ltx-2-3-reframe)
- [Grok](https://spiral.ai/integrations/grok/ltx-2-3-reframe)
- [Grok Build](https://spiral.ai/integrations/grok-build/ltx-2-3-reframe)
- [Hermes](https://spiral.ai/integrations/hermes/ltx-2-3-reframe)
- [Manus](https://spiral.ai/integrations/manus/ltx-2-3-reframe)
- [Muse](https://spiral.ai/integrations/muse/ltx-2-3-reframe)
- [Muse Code](https://spiral.ai/integrations/muse-code/ltx-2-3-reframe)
- [n8n](https://spiral.ai/integrations/n8n/ltx-2-3-reframe)
- [Notion](https://spiral.ai/integrations/notion/ltx-2-3-reframe)
- [OpenClaw](https://spiral.ai/integrations/openclaw/ltx-2-3-reframe)
- [opencode](https://spiral.ai/integrations/opencode/ltx-2-3-reframe)
- [Perplexity](https://spiral.ai/integrations/perplexity/ltx-2-3-reframe)
- [Raycast](https://spiral.ai/integrations/raycast/ltx-2-3-reframe)
- [VS Code](https://spiral.ai/integrations/vscode/ltx-2-3-reframe)
- [Windsurf](https://spiral.ai/integrations/windsurf/ltx-2-3-reframe)
- [Zapier](https://spiral.ai/integrations/zapier/ltx-2-3-reframe)

## More Instinct guides

- [LTX 2.3 Pro Text to Video](https://spiral.ai/integrations/instinct/ltx-2-3-pro-text-to-video)
- [LTX 2.5 Alpha Gen](https://spiral.ai/integrations/instinct/ltx-2-5-alpha-gen)
- [LTX 2.3 Pro Retake](https://spiral.ai/integrations/instinct/ltx-2-3-pro-retake)
- [LTX 2.5 Fast Audio to Video](https://spiral.ai/integrations/instinct/ltx-2-5-fast-audio-to-video)
- [LTX 2.3 Pro Image to Video](https://spiral.ai/integrations/instinct/ltx-2-3-pro-image-to-video)
- [LTX 2.5 Fast Image to Video](https://spiral.ai/integrations/instinct/ltx-2-5-fast-image-to-video)

## Questions about LTX 2.3 Reframe in Instinct

**Can Instinct use LTX 2.3 Reframe?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run LTX 2.3 Reframe like any built-in tool.

**How much does LTX 2.3 Reframe cost in Instinct?**

Up to $15.60 per run at the default inputs for 60 seconds of input. `resolution`: 720p $7.80, 1080p (default) $15.60. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need a fal account to use LTX 2.3 Reframe in Instinct?**

You need no fal account. Instinct uses one Spiral API key for every tool, and Spiral runs LTX 2.3 Reframe on its own fal account.

**How long does it take to set up LTX 2.3 Reframe in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while LTX 2.3 Reframe runs?**

LTX 2.3 Reframe runs in the background. Instinct starts the run, checks on it and gives you the video when it's ready.

**What is LTX 2.3 Reframe good for?**

It adapts existing footage to a different screen shape by generating areas beyond the original frame. That makes it useful when a conventional crop would remove people, products, or surrounding scenery.

**How long can a source clip be?**

The maximum is 60 seconds, with LTX also documenting a ceiling of 1,800 frames. A 60 fps source therefore reaches that ceiling at 30 seconds.

**Can LTX 2.3 Reframe produce 4K video?**

The documented output tiers are 720p and 1080p. Plan a separate step if your delivery requires 4K.

**Does reframing change the soundtrack?**

LTX documents that the input audio is copied without re-encoding. A silent source remains silent.

**Does it recover what the camera actually recorded outside the frame?**

The added areas are generated content based on the visible scene. Treat them as an interpretation, and review the expanded edges before using the result where visual accuracy matters.

