README.md

---
base_model:
- Wan-AI/Wan2.2-I2V-A14B
library_name: diffusers
license: apache-2.0
tags:
- diffusion-single-file
- comfyui
- distillation
- LoRA
- video
- video generation
- SGMD
pipeline_tag: image-to-video
---

# 🎬 Wan2.2 Distilled Models (SGMD)

This repository contains distilled versions of the Wan2.2 models using **SGMD (Score Gradient Matching Distillation)**, as presented in the paper [SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation](https://huggingface.co/papers/2605.30116).

### ⚡ High-Performance Video Generation with 4-Step Inference

*Distillation-accelerated version of Wan2.2 - Dramatically faster speed with excellent quality*

![img_lightx2v](https://cdn-uploads.huggingface.co/production/uploads/680de13385293771bc57400b/tTnp8-ARpj3wGxfo5P55c.png)

---

[![🤗 HuggingFace](https://img.shields.io/badge/🤗-HuggingFace-yellow)](https://huggingface.co/lightx2v/Wan2.2-Distill-Models)
[![GitHub](https://img.shields.io/badge/GitHub-LightX2V-blue?logo=github)](https://github.com/ModelTC/LightX2V)
[![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](LICENSE)

---

## 🔥 News

- 2026.04.12: We are excited to release the [Wan2.2-I2V-A14B-4step-720p-high](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_i2v_A14b_high_noise_lightx2v_4step_720p_260412.safetensors) and [Wan2.2-I2V-A14B-4step-720p-low](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_i2v_A14b_low_noise_lightx2v_4step_720p_260412.safetensors) models. Compared to previous iterations, this version was trained on a high-quality 720p dataset and features an optimized low-noise training algorithm. These enhancements significantly boost the model's performance in fine-grained detail rendering and visual texture.

## 🚀 Quick Usage (Python)

To use these models with the [LightX2V](https://github.com/ModelTC/LightX2V) framework for 4-step inference:

```python
from lightx2v import LightX2VPipeline

# Initialize pipeline for Wan2.2 I2V task
pipe = LightX2VPipeline(
    model_path="lightx2v/Wan2.2-Distill-Models",
    model_cls="wan2.2_moe",
    task="i2v",
)

# Enable offloading to reduce VRAM usage
pipe.enable_offload(
    cpu_offload=True,
    offload_granularity="block",
    text_encoder_offload=True,
)

# Create generator for 4-step inference
pipe.create_generator(
    attn_mode="sage_attn2",
    infer_steps=4,
    height=480,
    width=832,
    num_frames=81,
    guidance_scale=[1.0, 1.0],
)

# Generate video
pipe.generate(
    seed=42,
    image_path="path/to/your/image.jpg",
    prompt="A cinematic shot of a sunset over the ocean",
    save_result_path="output.mp4",
)
```

## 🌟 What's Special?

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

### ⚡ Ultra-Fast Generation
- **4-step inference** (vs traditional 50+ steps)
- Approximately **2x faster** using LightX2V than ComfyUI
- Near real-time video generation capability

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

### 🎯 Flexible Options
- **Dual noise control**: High/Low noise variants
- Multiple precision formats (BF16/FP8/INT8)
- Full 14B parameter models

</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
- Simple configuration files

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

---

## 📦 Model Catalog

### 🎥 Model Types

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

#### 🖼️ **Image-to-Video (I2V) - 14B Parameters**
Transform static images into dynamic videos with advanced quality control

- 🎨 **High Noise**: More creative, diverse outputs
- 🎯 **Low Noise**: More faithful to input, stable outputs

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

#### 📝 **Text-to-Video (T2V) - 14B Parameters**
Generate videos from text descriptions

- 🎨 **High Noise**: More creative, diverse outputs
- 🎯 **Low Noise**: More stable and controllable outputs
- 🚀 Full 14B parameter model

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

### 🎯 Precision Versions

| Precision | Model Identifier | Model Size | Framework | Quality vs Speed |
|:---------:|:-----------------|:----------:|:---------:|:-----------------|
| 🏆 **BF16** | `lightx2v_4step` | ~28.6 GB | LightX2V | ⭐⭐⭐⭐⭐ Highest Quality |
| ⚡ **FP8** | `scaled_fp8_e4m3_lightx2v_4step` | ~15 GB | LightX2V | ⭐⭐⭐⭐ Excellent Balance |
| 🎯 **INT8** | `int8_lightx2v_4step` | ~15 GB | LightX2V | ⭐⭐⭐⭐ Fast & Efficient |
| 🔷 **FP8 ComfyUI** | `scaled_fp8_e4m3_lightx2v_4step_comfyui` | ~15 GB | ComfyUI | ⭐⭐⭐ ComfyUI Ready |

---

## 🚀 Alternative Usage Methods

### Method 1: ComfyUI
Please refer to [workflow](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_moe_i2v_scale_fp8_comfyui.json)

## ⚠️ Important Notes

**Other Components**: These models only contain DIT weights. Additional components needed at runtime:
   - T5 text encoder
   - CLIP vision encoder
   - VAE encoder/decoder
   - Tokenizer

Please refer to [LightX2V Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/getting_started/model_structure.html) for instructions on organizing the complete model directory.

## 🤝 Community

- **GitHub Issues**: https://github.com/ModelTC/LightX2V/issues
- **HuggingFace**: https://huggingface.co/lightx2v/Wan2.2-Distill-Models

If you find this project helpful, please give us a ⭐ on [GitHub](https://github.com/ModelTC/LightX2V)