2026-05-26
Updates
- Gradio demo support: We have added a Gradio-based demo for running and testing the model through an interactive web interface.
- Multimodal inference tasks: The Gradio interface now supports Text-to-Video Generation, Video Edit, Video Understanding, Text-to-Image Generation, Image Edit, and Image Understanding in a unified UI.
- Local deployment: The Gradio app can be launched locally with the following command, making it easier to try the model without writing additional inference scripts.
python3 lance_gradio.py --server-name 0.0.0.0 --server-port 7860
Unified Multimodal Inference in the Gradio Interface