|
|
--- |
|
|
license: other |
|
|
license_link: https://huggingface.co/Lightricks/LTX-2/blob/main/LICENSE |
|
|
tags: |
|
|
- lora |
|
|
- video |
|
|
- text-to-video |
|
|
- camera-motion |
|
|
- jib-down |
|
|
- ltx |
|
|
base_model: Lightricks/LTX-2 |
|
|
model_type: lora |
|
|
--- |
|
|
|
|
|
# LTX-2 19B LoRA - Camera Control (Jib Down) |
|
|
|
|
|
This is a camera-motion control LoRA trained to bias generations toward a **jib-down** camera move on top of an **LTX-2 19B** base video model. |
|
|
|
|
|
- **Camera motion**: jib down (camera descends vertically, revealing more of what’s lower in the scene and changing parallax) |
|
|
- **Base model**: `Lightricks/LTX-2` |
|
|
- **Training type**: LoRA finetune for camera motion control |
|
|
|
|
|
## Model Details |
|
|
|
|
|
- **Developed by**: Lightricks |
|
|
- **Base model**: LTX-2 19B |
|
|
- **Model type**: LoRA |
|
|
- **Intended use**: text-to-video generation with controlled camera movement (jib down) |
|
|
|
|
|
## Recommended Prompting |
|
|
|
|
|
To get the best results with Motion Camera LoRAs, describe the **destination of the movement** and the **hidden parts of the scene** so the model knows what to reveal as the frame shifts. |
|
|
|
|
|
For a **jib-down** shot, explicitly mention what should come into view **near the bottom of the frame** as the camera descends (e.g., floor details, objects placed low, signage near ground level, lower levels of architecture). This gives the model a visual “map” of what exists below the initial framing. |
|
|
|
|
|
|
|
|
## License |
|
|
|
|
|
See the base model license: **Lightricks/LTX-2 LICENSE** (`https://huggingface.co/Lightricks/LTX-2/blob/main/LICENSE`). |
