Name: Wan2.2 Distill Loras
Author: lightx2v

Overview

Wan2.2 Distill LoRAs are specialized adapters designed to optimize image-to-video generation by leveraging knowledge distillation. For developers, these LoRAs significantly reduce the computational overhead required to maintain high temporal consistency and visual fidelity compared to full-parameter models. They are particularly effective for creating short, cinematic loops or animating static assets without the need for extensive hardware clusters. Integration is straightforward for those already using the Wan2.2 ecosystem, as these weights can be hot-swapped to shift style or motion dynamics. Compared to standard checkpoints, the distilled versions offer a better balance between inference speed and output quality, making them ideal for deploying real-time generative pipelines or scalable creative tools.

Highlights

Accelerated image-to-video inference via knowledge distillation
Reduced VRAM requirements for high-fidelity motion
Seamless integration with existing Wan2.2 frameworks
Apache-2.0 license for flexible commercial deployment
Improved temporal stability over base model weights

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("lightx2v/Wan2.2-Distill-Loras")
tokenizer = AutoTokenizer.from_pretrained("lightx2v/Wan2.2-Distill-Loras")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download lightx2v/Wan2.2-Distill-Loras

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download lightx2v/Wan2.2-Distill-Loras config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('lightx2v/Wan2.2-Distill-Loras')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/lightx2v/Wan2.2-Distill-Loras

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/lightx2v/Wan2.2-Distill-Loras

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('lightx2v/Wan2.2-Distill-Loras')
tokenizer = AutoTokenizer.from_pretrained('lightx2v/Wan2.2-Distill-Loras')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model lightx2v/Wan2.2-Distill-Loras

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model lightx2v/Wan2.2-Distill-Loras README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('lightx2v/Wan2.2-Distill-Loras')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/lightx2v/Wan2.2-Distill-Loras.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/lightx2v/Wan2.2-Distill-Loras.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'lightx2v/Wan2.2-Distill-Loras')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
tags:

diffusion-single-file

comfyui

distillation

LoRA

video

video genration

lora

pipeline_tags:

image-to-video

text-to-video

base_model:

Wan-AI/Wan2.2-I2V-A14B

library_name: diffusers
pipeline_tag: image-to-video
---

🎬 Wan2.2 Distilled LoRA Models

⚡ High-Performance Video Generation with 4-Step Inference Using LoRA

*LoRA weights extracted from Wan2.2 distilled models - Flexible deployment with excellent generation quality*

!img_lightx2v

---

![🤗 HuggingFace](https://huggingface.co/lightx2v/Wan2.2-Distill-Loras)
![GitHub](https://github.com/ModelTC/LightX2V)
![License](LICENSE)

---

🌟 What's Special?

⚡ Flexible Deployment

Base Model + LoRA: Can be combined with base models

Offline Merging: Pre-merge LoRA into models

Online Loading: Dynamically load LoRA during inference

Multiple Frameworks: Supports LightX2V and ComfyUI

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

🎯 Dual Noise Control

High Noise: More creative, diverse outputs

Low Noise: More faithful to input, stable outputs

Rank 64 LoRA, compact size

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

💾 Storage Efficient

Small LoRA Size: Significantly smaller than full models

Flexible Combination: Can be combined with quantization

Easy Sharing: Convenient for model weight distribution

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

🚀 4-Step Inference

Ultra-Fast Generation: Generate high-quality videos in just 4 steps

Distillation Acceleration: Inherits advantages of distilled models

Quality Assurance: Maintains excellent generation quality

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

---

📦 LoRA Model Catalog

🎥 Available LoRA Models

| Task Type | Noise Level | Model File | Rank | Purpose |
|:-------:|:--------:|:---------|:----:|:-----|
| I2V | High Noise | wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_xxx.safetensors | 64 | More creative image-to-video |
| I2V | Low Noise | wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_xxx.safetensors | 64 | More stable image-to-video |

> 💡 Note:
> - xxx in filenames represents version number or timestamp, please check HuggingFace repository for the latest version
> - These LoRAs must be used with Wan2.2 base models

---

🚀 Usage

Prerequisites

Base Model: You need to prepare Wan2.2 I2V base model (original model without distillation)

Download base model (choose one):

Method 1: From LightX2V Official Repository (Recommended)

bash

# Download high noise base model
huggingface-cli download lightx2v/Wan2.2-Official-Models \
    wan2.2_i2v_A14b_high_noise_lightx2v.safetensors \
    --local-dir ./models/Wan2.2-Official-Models
Download low noise base model
huggingface-cli download lightx2v/Wan2.2-Official-Models \
    wan2.2_i2v_A14b_low_noise_lightx2v.safetensors \
    --local-dir ./models/Wan2.2-Official-Models

Method 2: From Wan-AI Official Repository

bash

huggingface-cli download Wan-AI/Wan2.2-I2V-A14B \
    --local-dir ./models/Wan2.2-I2V-A14B

> 💡 Note: lightx2v/Wan2.2-Official-Models provides separate high noise and low noise base models, download as needed

Method 1: LightX2V - Offline LoRA Merging (Recommended ⭐)

Offline LoRA merging provides best performance and supports quantization simultaneously.

#### 1.1 Download LoRA Models

bash

# Download both LoRAs (high noise and low noise)
Note: xxx represents version number, please check HuggingFace for actual filename
huggingface-cli download lightx2v/Wan2.2-Distill-Loras \
    wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    --local-dir ./loras/

#### 1.2 Merge LoRA (Basic Merging)

Merge LoRA:

bash

cd LightX2V/tools/convert
For directory-based base model: --source /path/to/Wan2.2-I2V-A14B/high_noise_model/
python converter.py \
    --source ./models/Wan2.2-Official-Models/wan2.2_i2v_A14b_high_noise_lightx2v.safetensors \
    --output /path/to/output/ \
    --output_ext .safetensors \
    --output_name wan2.2_i2v_A14b_high_noise_lightx2v_4step \
    --model_type wan_dit \
    --lora_path /path/to/loras/wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    --lora_strength 1.0 \
    --single_file
For directory-based base model: --source /path/to/Wan2.2-I2V-A14B/low_noise_model/
python converter.py \
    --source ./models/Wan2.2-Official-Models/wan2.2_i2v_A14b_low_noise_lightx2v.safetensors \
    --output /path/to/output/ \
    --output_ext .safetensors \
    --output_name wan2.2_i2v_A14b_low_noise_lightx2v_4step \
    --model_type wan_dit \
    --lora_path /path/to/loras/wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    --lora_strength 1.0 \
    --single_file

#### 1.3 Merge LoRA + Quantization (Recommended)

Merge LoRA + FP8 Quantization:

bash

cd LightX2V/tools/convert
For directory-based base model: --source /path/to/Wan2.2-I2V-A14B/high_noise_model/
python converter.py \
    --source ./models/Wan2.2-Official-Models/wan2.2_i2v_A14b_high_noise_lightx2v.safetensors \
    --output /path/to/output/ \
    --output_ext .safetensors \
    --output_name wan2.2_i2v_A14b_high_noise_scaled_fp8_e4m3_lightx2v_4step \
    --model_type wan_dit \
    --lora_path /path/to/loras/wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    --lora_strength 1.0 \
    --quantized \
    --linear_dtype torch.float8_e4m3fn \
    --non_linear_dtype torch.bfloat16 \
    --single_file
For directory-based base model: --source /path/to/Wan2.2-I2V-A14B/low_noise_model/
python converter.py \
    --source ./models/Wan2.2-Official-Models/wan2.2_i2v_A14b_low_noise_lightx2v.safetensors \
    --output /path/to/output/ \
    --output_ext .safetensors \
    --output_name wan2.2_i2v_A14b_low_noise_scaled_fp8_e4m3_lightx2v_4step \
    --model_type wan_dit \
    --lora_path /path/to/loras/wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    --lora_strength 1.0 \
    --quantized \
    --linear_dtype torch.float8_e4m3fn \
    --non_linear_dtype torch.bfloat16 \
    --single_file

Merge LoRA + ComfyUI FP8 Format:

bash

cd LightX2V/tools/convert
For directory-based base model: --source /path/to/Wan2.2-I2V-A14B/high_noise_model/
python converter.py \
    --source ./models/Wan2.2-Official-Models/wan2.2_i2v_A14b_high_noise_lightx2v.safetensors \
    --output /path/to/output/ \
    --output_ext .safetensors \
    --output_name wan2.2_i2v_A14b_high_noise_scaled_fp8_e4m3_lightx2v_4step_comfyui \
    --model_type wan_dit \
    --lora_path /path/to/loras/wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    --lora_strength 1.0 \
    --quantized \
    --linear_dtype torch.float8_e4m3fn \
    --non_linear_dtype torch.bfloat16 \
    --single_file \
    --comfyui_mode
For directory-based base model: --source /path/to/Wan2.2-I2V-A14B/low_noise_model/
python converter.py \
    --source ./models/Wan2.2-Official-Models/wan2.2_i2v_A14b_low_noise_lightx2v.safetensors \
    --output /path/to/output/ \
    --output_ext .safetensors \
    --output_name wan2.2_i2v_A14b_low_noise_scaled_fp8_e4m3_lightx2v_4step_comfyui \
    --model_type wan_dit \
    --lora_path /path/to/loras/wan2.2_i2v_A14b_low_noise_lora_rank64_lightx2v_4step_xxx.safetensors \
    --lora_strength 1.0 \
    --quantized \
    --linear_dtype torch.float8_e4m3fn \
    --non_linear_dtype torch.bfloat16 \
    --single_file \
    --comfyui_mode