Hugging Face's logo

Lightricks
/
LTX-2-19b-LoRA-Camera-Control-Static

Text-to-Video
LTX-2
lora
ltx-2
video-generation
camera-control
static-camera
Model card Files
xet
 Community
2
How to use from the
Use from the
LTX-2 library
# 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-Static --local-dir models/LTX-2-19b-LoRA-Camera-Control-Static
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-Static/<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

LTX-2 19B LoRA - Camera Control (Static)

This is a camera-motion control LoRA trained to bias generations toward a static camera (no intentional camera translation, pan, tilt, roll, or zoom) 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 control (static / locked-off)

License

See the base model license: Lightricks/LTX-2 LICENSE.

Downloads last month
-
Inference Providers NEW
Text-to-Video

This task can take several minutes

Model tree for Lightricks/LTX-2-19b-LoRA-Camera-Control-Static

Base model

Lightricks/LTX-2
Adapter
(55)
this model

Spaces using Lightricks/LTX-2-19b-LoRA-Camera-Control-Static 58

Collection including Lightricks/LTX-2-19b-LoRA-Camera-Control-Static