LightX2V is an advanced lightweight video generation inference framework engineered to deliver efficient, high-performance video synthesis solutions. This unified platform integrates multiple state-of-the-art video generation techniques, supporting diverse generation tasks including text-to-video (T2V) and image-to-video (I2V). X2V represents the transformation of different input modalities (X, such as text or images) into video output (V).
For comprehensive usage instructions, please refer to our documentation: English Docs | δΈζζζ‘£
- β HunyuanVideo
- β Wan2.1
- β SkyReels-V2-DF
- β CogVideoX1.5-5B-T2V
- β Wan2.1-T2V-1.3B-Lightx2v
- β Wan2.1-T2V-14B-Lightx2v
- β Wan2.1-I2V-14B-480P-Lightx2v
- β Wan2.1-I2V-14B-720P-Lightx2v
- β Wan2.1-T2V-14B-StepDistill-CfgDistill-Lightx2v
- β Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v
- β Wan2.1-I2V-14B-720P-StepDistill-CfgDistill-Lightx2v
- π₯ SOTA Inference Speed: Achieve ~20x acceleration via step distillation and system optimization (single GPU)
- β‘οΈ Revolutionary 4-Step Distillation: Compress original 40-50 step inference to just 4 steps without CFG requirements
- π οΈ Advanced Operator Support: Integrated with cutting-edge operators including Sage Attention, Flash Attention, Radial Attention, q8-kernel, sgl-kernel, vllm
- π‘ Breaking Hardware Barriers: Run 14B models for 480P/720P video generation with only 8GB VRAM + 16GB RAM
- π§ Intelligent Parameter Offloading: Advanced disk-CPU-GPU three-tier offloading architecture with phase/block-level granular management
- βοΈ Comprehensive Quantization: Support for
w8a8-int8,w8a8-fp8,w4a4-nvfp4and other quantization strategies
- π Smart Feature Caching: Intelligent caching mechanisms to eliminate redundant computations
- π Parallel Inference: Multi-GPU parallel processing for enhanced performance
- π± Flexible Deployment Options: Support for Gradio, service deployment, ComfyUI and other deployment methods
- ποΈ Dynamic Resolution Inference: Adaptive resolution adjustment for optimal generation quality
For detailed performance metrics and comparisons, please refer to our benchmark documentation.
Detailed Service Deployment Guide β
- Model Quantization - Comprehensive guide to quantization strategies
- Feature Caching - Intelligent caching mechanisms
- Attention Mechanisms - State-of-the-art attention operators
- Parameter Offloading - Three-tier storage architecture
- Parallel Inference - Multi-GPU acceleration strategies
- Step Distillation - 4-step inference technology
- Low-Resource Deployment - Optimized 8GB VRAM solutions
- Low-Latency Deployment - Ultra-fast inference optimization
- Gradio Deployment - Web interface setup
- Service Deployment - Production API service deployment
We maintain code quality through automated pre-commit hooks to ensure consistent formatting across the project.
Tip
Setup Instructions:
- Install required dependencies:
pip install ruff pre-commit- Run before committing:
pre-commit run --all-filesWe appreciate your contributions to making LightX2V better!
We extend our gratitude to all the model repositories and research communities that inspired and contributed to the development of LightX2V. This framework builds upon the collective efforts of the open-source community.
If you find LightX2V useful in your research, please consider citing our work:
@misc{lightx2v,
author = {LightX2V Contributors},
title = {LightX2V: Light Video Generation Inference Framework},
year = {2025},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/ModelTC/lightx2v}},
}For questions, suggestions, or support, please feel free to reach out through:
- π GitHub Issues - Bug reports and feature requests
- π¬ GitHub Discussions - Community discussions and Q&A
![@gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=64&v=4){kind=small}