Instructions to use Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LTX.io
How to use Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left 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 Lightricks/LTX-2-19b-LoRA-Camera-Control-Dolly-Left --local-dir models/LTX-2-19b-LoRA-Camera-Control-Dolly-Left 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-Dolly-Left/<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
| license: other | |
| license_link: https://huggingface.co/Lightricks/LTX-2/blob/main/LICENSE | |
| tags: | |
| - lora | |
| - video | |
| - text-to-video | |
| - camera-motion | |
| - dolly-left | |
| - ltx | |
| base_model: Lightricks/LTX-2 | |
| model_type: lora | |
| pipeline_tag: text-to-video | |
| # LTX-2 19B LoRA - Camera Control (Dolly Left) | |
| This is a camera-motion control **LoRA** trained to bias generations toward a **dolly-left** camera move (camera translates laterally to the left, revealing content on the left side of the scene and changing parallax) on top of an **LTX-2 19B** base video model. | |
| ## Model Details | |
| - **Developed by**: Lightricks | |
| - **Base model**: LTX-2 19B | |
| - **Training type**: LoRA finetune for camera motion (dolly left) | |
| ## 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 dolly-left shot, explicitly mention what should come into view on the **left side** during the move (e.g., the far-left side of a room, objects/people positioned off-frame to the left, background structures that become visible due to parallax). This gives the model a visual “map” of what exists as the camera slides left. | |
| ## License | |
| License link: `https://huggingface.co/Lightricks/LTX-2/blob/main/LICENSE` | |
| See the base model license: [`Lightricks/LTX-2 LICENSE`](https://huggingface.co/Lightricks/LTX-2/blob/main/LICENSE). |