---
base_model:
- Lightricks/LTX-2.3
tags:
- video-generation
- lora
- ic-lora
- ltx-video
- camera-motion
- lightricks
widget:
- text: >-
    point-of-view of a spaceship flying above an asteroid while chasing an
    X-Wing spaceship, firing green laser beams
  output:
    url: assets/test-compa_00007.mp4
- text: >-
    woman walks on a rainy street. the camera zooms out and upwards showing the
    city around
  output:
    url: assets/test-compa_00016.mp4
- text: girl is sitting on the bed while the camera pans left
  output:
    url: assets/test-compa_00001.mp4
- text: woman walking with blowing magical halo behind her head
  output:
    url: assets/test-compa_00012.mp4
- text: woman casting magic orbs with her hands
  output:
    url: assets/test-compa_00011.mp4
- text: woman in black armor stands still and starts to salute
  output:
    url: assets/test-compa_00009.mp4
- text: woman sitting on the bed holding a smoking gun
  output:
    url: assets/test-compa_00013.mp4
- text: ballerina walks slowly
  output:
    url: assets/test-compa_00008.mp4
- text: woman is walking across the room
  output:
    url: assets/test-compa_00015.mp4
- text: woman standing in a narrow storage room
  output:
    url: assets/test-compa_00014.mp4
- text: '""'
  output:
    url: assets/test-compa_00002.mp4
- text: '""'
  output:
    url: assets/test-compa_00003.mp4
---

# LTX-Video 2.3 22B — IC-LoRA: Cameraman v2

A fine-tuned In-Context LoRA (IC-LoRA) adapter for LTX-Video 2.3 (22B),
trained to replicate camera movements from a reference video.

This is **v2** of the [Cameraman IC-LoRA](https://huggingface.co/Cseti/LTX2.3-22B_IC-LoRA-Cameraman_v1) with
a larger and more diverse dataset.

## Example outputs

Each video shows the reference (camera-motion input) and the generated output.

<Gallery />

## Usage (ComfyUI)

I tested this lora only in **ComfyUI**. An example workflow is here:
https://huggingface.co/datasets/Cseti/ComfyUI-Workflows/blob/main/ltx/2.3/ic-lora-cameraman-v2/README.md

How it works:
- Load `LTX2.3-22B_IC-LoRA-Cameraman_v2_14000.safetensors` as the LoRA.
- Provide a **reference video** carrying the camera motion you want to replicate.
- Provide a **starting image**. This is optional. The model works both in T2V or I2V mode.
- Provide a **text prompt** describing the scene to generate.
- No trigger word is needed.

## Tips

- **Resolution:** based on my testing, the higher the resolution, the more closely
  the reference camera motion is followed. I wouldn't go below **960x512** for the first pass.
- **Image (conditioning) strength:** use an image strength of **0.5 or 0.7** for more motion.
- **The prompt matters a lot** — it strongly affects the camera movement. If the output
  doesn't follow the reference camera motion, you can try:
  - leaving the prompt empty (in some cases this works best),
  - a different seed,
  - describing the camera motion explicitly, at least at a high level.

## Training Details

This IC-LoRA was trained on [RunPod cloud GPUs](https://runpod.io?ref=vpp0cion)
(NVIDIA RTX PRO 6000 Blackwell, 96 GB).

| Parameter | Value |
|---|---|
| Base model | LTX-Video 2.3 (22B) |
| Training framework | ltx-trainer (Lightricks) |
| Training strategy | IC-LoRA (video_to_video) |
| Released checkpoint | step 14,000 |
| LoRA rank / alpha | 64 / 64 |
| Target modules | attn1, attn2 (to_k/q/v/out), ff.net.0.proj, ff.net.2 |
| Optimizer | ProdigyPlusScheduleFree (auto-LR, prodigy_steps 1000) |
| Scheduler | constant (required by schedule-free) |
| Mixed precision | bf16 |
| Batch size | 1 (gradient checkpointing enabled) |
| Training dataset | 343 video pairs (+ 23 held-out for validation loss) |
| Resolution buckets | 768x512x{57,89,113,121} @ 24fps |
| First frame conditioning | 0.3 |

### Dataset

366 curated reference/target pairs (343 train / 23 held-out validation, 0 overlap). The set covers
single-axis motions as well as many compound multi-axis combinations
(e.g. pan_left + tilt_up + roll_ccw, dolly_in + truck_left + pedestal_down).

Motion-component frequency across the training set (a pair can contribute to
several components):

| Component | Count |
|---|---|
| pan_right | 93 |
| pan_left | 90 |
| dolly_in | 83 |
| roll_cw | 79 |
| truck_right | 79 |
| roll_ccw | 77 |
| tilt_up | 75 |
| zoom_in | 69 |
| truck_left | 68 |
| tilt_down | 62 |
| dolly_out | 61 |
| zoom_out | 52 |
| pedestal_down | 50 |
| static | 28 |
| pedestal_up | 25 |

Of the 343 training pairs, 93 are single-axis and 250 are compound (multi-axis).

## Limitations

- Complex compound motions may not transfer reliably

## License

This LoRA is created as part of a personal 
project for research purposes only and is not intended for commercial use. 

## Support

Producing and sharing this kind of open-source work requires renting cloud GPUs, which gets expensive quickly. If you find it useful and would like me to keep contributing, your support is very much appreciated:

[![Ko-fi](https://img.shields.io/badge/Ko--fi-Support-FF5E5B?style=for-the-badge&logo=ko-fi&logoColor=white)](https://ko-fi.com/chetyart) [![Liberapay](https://img.shields.io/badge/Liberapay-Donate-F6C915?style=for-the-badge&logo=liberapay&logoColor=black)](https://liberapay.com/chetyart/donate)