# Download the weights from this repo, plus the Gemma text encoder
hf download SyFeee/LTX-2.3-SyFe-Union-Control --local-dir models/LTX-2.3-SyFe-Union-Control
hf download google/gemma-3-12b-it-qat-q4_0-unquantized --local-dir models/gemma-3-12b# Video-to-video with the IC-LoRA (runs on the distilled base model)
uv run python -m ltx_pipelines.ic_lora \
--distilled-checkpoint-path path/to/distilled_checkpoint.safetensors \
--spatial-upsampler-path path/to/spatial_upsampler.safetensors \
--gemma-root models/gemma-3-12b \
--lora models/LTX-2.3-SyFe-Union-Control/<weights>.safetensors 1.0 \
--video-conditioning reference.mp4 1.0 \
--prompt "your prompt here" \
--output-path output.mp4SyFe LTX-2.3 Union-Control LoRA
SyFe-trained full-attention IC-LoRA combining Canny, depth, and pose control for LTX-2.3 22B-dev.
Checkpoint
union_control_bal was trained for 5,000 steps at rank 128 on a balanced 19,740-row control corpus: 6,580 Canny, 6,580 depth, and 6,580 pose examples. Training used video_to_video conditioning at 1280x704 with reference scale 1.0.
The final checkpoint and exact training configuration are under runs/union_control_bal/.
Status
Training completed, but the final checkpoint has not received a complete production-quality validation pass. Treat this as a research checkpoint and evaluate each control mode independently before deployment. This is not the downloaded Lightricks Union-Control adapter and does not replace the separately published SyFe pose, depth, and Canny repositories.
Use is subject to the LTX-2 community license.
- Downloads last month
- 12
Model tree for SyFeee/LTX-2.3-SyFe-Union-Control
Base model
Lightricks/LTX-2.3
# Install the LTX-2 pipelines git clone https://github.com/Lightricks/LTX-2.git cd LTX-2 uv sync --frozen