Instructions to use editedge/LTX-2-19b-LoRA-Camera-Control-Jib-Down with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use editedge/LTX-2-19b-LoRA-Camera-Control-Jib-Down with LTX.io:
# 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 editedge/LTX-2-19b-LoRA-Camera-Control-Jib-Down --local-dir models/LTX-2-19b-LoRA-Camera-Control-Jib-Down 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-Down/<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
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).
- Downloads last month
- -
Model tree for editedge/LTX-2-19b-LoRA-Camera-Control-Jib-Down
Base model
Lightricks/LTX-2