About LTX 2.3 Extend
LTX 2.3 Extend continues an existing clip, adding 2 to 20 seconds of new footage at its start or end. Audio is generated for the added portion when the input video has audio.
The input video keeps its resolution and supports 16:9 and 9:16 clips up to 4K; the extension plus the context it draws on is capped at about 21 seconds at 24 FPS.
Ready to build with LTX 2.3 Extend?
Try LTX 2.3 Extend in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "ltx-2-3-extend",
"input_video": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/videos/waterfall.mp4",
"duration": 6,
"extend_mode": "end"
}'Request parameters
Every field LTX 2.3 Extend accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
input_video | stringuri | Yes | — | The clip to extend. 16:9 or 9:16, up to 4K, at least 3 seconds. |
prompt | string | No | — | Optional description of what happens in the added footage. |
duration | integer | No | 6 | Range: 2 – 20 |
extend_mode | string | No | "end" | Add the new footage at the start or the end of the clip.startend |
context | number | No | — | Seconds of the input video to use as context, up to 20. Defaults to 5 (less for long extensions). Context seconds are billed with the extension. Range: 1 – 20 |