Instructions to use Lightricks/LTX-2-19b-LoRA-Camera-Control-Jib-Up with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX-2
How to use Lightricks/LTX-2-19b-LoRA-Camera-Control-Jib-Up with LTX-2:
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen
# Download the weights from this repo, plus the Gemma text encoder hf download Lightricks/LTX-2-19b-LoRA-Camera-Control-Jib-Up --local-dir models/LTX-2-19b-LoRA-Camera-Control-Jib-Up hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b
# Text/image-to-video with the LoRA on the HQ two-stage base pipeline uv run python -m ltx_pipelines.ti2vid_two_stages_hq \ --checkpoint-path path/to/checkpoint.safetensors \ --distilled-lora path/to/distilled_lora.safetensors 0.8 \ --spatial-upsampler-path path/to/spatial_upsampler.safetensors \ --gemma-root models/gemma-3-12b \ --lora models/LTX-2-19b-LoRA-Camera-Control-Jib-Up/<weights>.safetensors 1.0 \ --prompt "your prompt here" \ --output-path output.mp4 # For image-to-video, add: --image path/to/image.jpg 0 0.8 - Inference
- Notebooks
- Google Colab
- Kaggle
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# LTX-2 19B LoRA — Camera Control (Jib Up)
|
| 3 |
+
|
| 4 |
+
This is a **camera-motion control LoRA** trained to bias generations toward a **jib-up camera move** (camera rises vertically) on top of an **LTX-2 19B** base video model.
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
## Model Details
|
| 8 |
+
|
| 9 |
+
- **Developed by** Lightricks
|
| 10 |
+
- **Base Model**: LTX-2 19B
|
| 11 |
+
- **Training Type**: LoRA finetune for camera motion (jib up)
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
## Recommended Prompting
|
| 15 |
+
|
| 16 |
+
- To get the best results with Motion Camera LoRAs, you should describe the "destination" of the movement and the hidden parts of the scene
|
| 17 |
+
- so the AI knows exactly what to reveal as the frame shifts. By detailing what exists at the end of the shot—such as the far side of a
|
| 18 |
+
- room or the sky above—you provide the model with a visual "map" that ensures spatial consistency.
|