---
license: apache-2.0
language:
- en
- zh
pipeline_tag: image-to-video
tags:
  - video generation
  - diffusion-single-file
  - comfyui
  - distillation
  - LoRA
  - quantization
  - nvfp4
library_name: diffusers
inference:
  parameters:
    num_inference_steps: 4
base_model:
- lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v
base_model_relation: quantized
---
# Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v-NVFP4

<p align="center">
    <img src="assets/img_lightx2v.png" width=33%/>
<p>

## Overview
This is a **partial NVFP4 quantization** of [Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v](https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v) by lightx2v.

Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v is an advanced image-to-video generation model built upon the Wan2.1-I2V-14B-480P foundation. This approach allows the model to generate videos with significantly fewer inference steps (4 steps) and without classifier-free guidance, substantially reducing video generation time while maintaining quality.

<div style="display: flex; align-items: center; gap: 16px;">
  <img src="assets/wan21_input_cat.png" width="45%"/>
  <span style="font-size: 2em;">➡</span>
  <video src="https://huggingface.co/InsecureErasure/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v-NVFP4/resolve/main/assets/wan21_output_cat.mp4" width="45%" controls></video>
</div>

## Quantization
The model weights have been partially quantized to **NVFP4** (NVIDIA Floating Point 4-bit), a quantization format supported on NVIDIA Blackwell architecture GPUs. Only a subset of the model layers have been quantized; the remaining layers are kept at their original precision to preserve output quality.

## License Agreement
The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generate contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the [license](LICENSE.txt).

## Acknowledgements
Many thanks to the contributors to the [Wan2.1](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B), [Self-Forcing](https://huggingface.co/gdhe17/Self-Forcing/tree/main) repositories, for their open research.