Instructions to use tqliu/Light-X with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tqliu/Light-X with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tqliu/Light-X", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
metadata
license: other
license_name: license
license_link: https://github.com/TQTQliu/Light-X/blob/master/LICENSE
tags:
- computer-vision
- video-generation
- video-editing
- 4d
- relighting
- camera-control
Light-X
📄 Paper | 🚀 Project Page | 💻 GitHub
Introduction
This repository provides the pretrained Light-X weights supporting text-based and background-image–conditioned video relighting and controllable view synthesis.
Citation
If you find our work useful for your research, please consider citing our paper:
@article{liu2025light,
title={Light-X: Generative 4D Video Rendering with Camera and Illumination Control},
author={Liu, Tianqi and Chen, Zhaoxi and Huang, Zihao and Xu, Shaocong and Zhang, Saining and Ye, Chongjie and Li, Bohan and Cao, Zhiguo and Li, Wei and Zhao, Hao and others},
journal={arXiv preprint arXiv:2512.05115},
year={2025}
}