lightx2v/Wan2.1-Distill-Models

<div align="center">

🎬 Wan2.1 Distilled Models

⚡ High-Performance Video Generation with 4-Step Inference

Distillation-accelerated versions of Wan2.1 - Dramatically faster while maintaining exceptional quality

  

</div>

🌟 What's Special?

<table> <tr> <td width="50%">

⚡ Ultra-Fast Generation

• —4-step inference (vs traditional 50+ steps)
• —Up to 2x faster than ComfyUI
• —Real-time video generation capability

</td> <td width="50%">

🎯 Flexible Options

• —Multiple resolutions (480P/720P)
• —Various precision formats (BF16/FP8/INT8)
• —I2V and T2V support

</td> </tr> <tr> <td width="50%">

💾 Memory Efficient

• —FP8/INT8: ~50% size reduction
• —CPU offload support
• —Optimized for consumer GPUs

</td> <td width="50%">

🔧 Easy Integration

• —Compatible with LightX2V framework
• —ComfyUI support available
• —Simple configuration files

</td> </tr> </table>

📦 Model Catalog

🎥 Model Types

<table> <tr> <td align="center" width="50%">

🖼️ Image-to-Video (I2V)

Transform still images into dynamic videos

• —📺 480P Resolution
• —🎬 720P Resolution

</td> <td align="center" width="50%">

📝 Text-to-Video (T2V)

Generate videos from text descriptions

• —🚀 14B Parameters
• —🎨 High-quality synthesis

</td> </tr> </table>

🎯 Precision Variants

📝 Naming Convention

# Pattern: wan2.1_{task}_{resolution}_{precision}.safetensors

# Examples:
wan2.1_i2v_720p_lightx2v_4step.safetensors                          # 720P I2V - BF16
wan2.1_i2v_720p_scaled_fp8_e4m3_lightx2v_4step.safetensors         # 720P I2V - FP8
wan2.1_i2v_480p_int8_lightx2v_4step.safetensors                    # 480P I2V - INT8
wan2.1_t2v_14b_scaled_fp8_e4m3_lightx2v_4step_comfyui.safetensors  # T2V - FP8 ComfyUI

💡 Explore all models: Browse Full Model Collection →

🚀 Usage

LightX2V is a high-performance inference framework optimized for these models, approximately 2x faster than ComfyUI with better quantization accuracy. Highly recommended!

Quick Start

1. 1.Download model (720P I2V FP8 example)

huggingface-cli download lightx2v/Wan2.1-Distill-Models \
    --local-dir ./models/wan2.1_i2v_720p \
    --include "wan2.1_i2v_720p_scaled_fp8_e4m3_lightx2v_4step.safetensors"

1. 1.Clone LightX2V repository

git clone https://github.com/ModelTC/LightX2V.git
cd LightX2V

1. 1.Install dependencies

pip install -r requirements.txt

Or refer to Quick Start Documentation to use docker

1. 1.Select and modify configuration file

Choose the appropriate configuration based on your GPU memory:

For 80GB+ GPU (A100/H100)

• —I2V: wan_i2v_distill_4step_cfg.json
• —T2V: wan_t2v_distill_4step_cfg.json

For 24GB+ GPU (RTX 4090)

• —I2V: wan_i2v_distill_4step_cfg_4090.json
• —T2V: wan_t2v_distill_4step_cfg_4090.json

1. 1.Run inference

cd scripts
bash wan/run_wan_i2v_distill_4step_cfg.sh

Documentation

• —Quick Start Guide: LightX2V Quick Start
• —Complete Usage Guide: LightX2V Model Structure Documentation
• —Configuration Guide: Configuration Files
• —Quantization Usage: Quantization Documentation
• —Parameter Offload: Offload Documentation

Performance Advantages

• —⚡ Fast: Approximately 2x faster than ComfyUI
• —🎯 Optimized: Deeply optimized for distilled models
• —💾 Memory Efficient: Supports CPU offload and other memory optimization techniques
• —🛠️ Flexible: Supports multiple quantization formats and configuration options

Community

• —Issues: https://github.com/ModelTC/LightX2V/issues

⚠️ Important Notes

1. 1.Additional Components: These models only contain DIT weights. You also need:
2. 2.T5 text encoder
3. 3.CLIP vision encoder
4. 4.VAE encoder/decoder
5. 5.Tokenizers

Refer to LightX2V Documentation for how to organize the complete model directory.

If you find this project helpful, please give us a ⭐ on GitHub