About LTX-2.3 Pro (IC-LoRA)
LTX-2.3 Pro (IC-LoRA) fine-tunes an in-context LoRA that transforms one video into another under the guidance of a reference video, such as a depth, pose or edge render. Train it on paired rows of a target video, a reference video with the same frame count, and a caption.
The adapter it produces requires a reference video at inference time. Base LTX-2.3 has no video-conditioning path of its own, so reference-video control is only available through an IC-LoRA. Use the standard LTX-2.3 Pro entry for text-to-video and image-to-video fine-tunes.
| Metric | Value |
|---|---|
| Parameter Count | 22 billion |
| Mixture of Experts | No |
Ready to build with LTX-2.3 Pro (IC-LoRA)?
Try LTX-2.3 Pro (IC-LoRA) 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-pro-ic-lora",
"prompt": "A cat sitting on a chair",
"input_video": "https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/videos/waterfall.mp4",
"duration": 6,
"fps": 24,
"width": 1536,
"height": 1024,
"video_conditioning_strength": 1,
"conditioning_attention_strength": 1
}'Request parameters
Every field LTX-2.3 Pro (IC-LoRA) accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text prompt describing the video to generate |
input_video | stringuri | Yes | — | Reference video that guides generation, e.g. a depth, pose or edge render. Required -- an IC-LoRA adapter has nothing to condition on without it. |
input_image | stringuri | No | — | Optional first frame image for image conditioning |
duration | integer | No | 6 | Range: 6 – 10 |
fps | integer | No | 24 | Frame rate in frames per second242530485060 |
width | integer | No | 1536 | Output width in pixels. Must be a multiple of 32. Range: 32 – 3840 |
height | integer | No | 1024 | Output height in pixels. Must be a multiple of 32. Range: 32 – 2160 |
video_conditioning_strength | number | No | 1 | Strength applied to the reference video. Range: 0 – 1 |
conditioning_attention_strength | number | No | 1 | Attention strength applied to conditioning inputs. Range: 0 – 1 |
seed | integer | No | — | Random seed for reproducible generation |