lightx2v / Wan-NVFP4

huggingface.co
Total runs: 473
24-hour runs: 0
7-day runs: 117
30-day runs: 112
Model's Last Updated: 2025年12月23日

Introduction of Wan-NVFP4

Model Details of Wan-NVFP4

🎬 Wan-NVFP4-4Steps Models

NVFP4 Quantization-Aware Step Distillation for Blackwell Architecture

GitHub HuggingFace

📋 Table of Contents
✨ Features
  • ⚡ 4-Step Inference : Dramatically accelerated end-to-end generation approaching real-time performance (tested on RTX 5090 single GPU)
  • 🎯 NVFP4 Quantization : Reduced memory and bandwidth usage, optimized for Blackwell architecture
  • 🔧 LightX2V Integration : Optimal performance and stability on the official framework
  • 🚀 High-Quality Generation : Maintains Wan2.1's superior video quality while achieving unprecedented speed
🚀 Quick Start
# 1. Install LightX2V
git clone https://github.com/ModelTC/LightX2V.git
cd LightX2V
uv pip install -v .

# 2. Install NVFP4 Kernel
pip install scikit_build_core uv
git clone https://github.com/NVIDIA/cutlass.git
cd lightx2v_kernel

MAX_JOBS=$(nproc) CMAKE_BUILD_PARALLEL_LEVEL=$(nproc) \
uv build --wheel \
  -Cbuild-dir=build . \
  -Ccmake.define.CUTLASS_PATH=/path/to/cutlass \
  --verbose --color=always --no-build-isolation

pip install dist/*whl --force-reinstall --no-deps

# 3. Run inference
cd examples/wan
python wan_i2v_nvfp4.py   # Image-to-Video
python wan_t2v_nvfp4.py   # Text-to-Video
🎬 Generation Results

"A cinematic, hyper-realistic 3D animation, in the somber and beautiful style of Sekiro: Shadows Die Twice. In a vast field of silvery-white pampas grass, under a luminous full moon, the shinobi Wolf stands ready for a final duel..."

Input Image Wan2.1-I2V-14B-480P wan2.1_i2v_480p_nvfp4_lightx2v_4step

"高对比度,高饱和度,短边构图,日落,中焦距,柔光,背光,暖色调,边缘光,中近景,日光,晴天光,一位外国白人女性的近景,她身穿黄色格子连衣裙,戴着耳环。随着仰拍镜头的上升,女子抬起头来,眼睛里含着泪水,看着前方说着话..."

Wan2.1-T2V-1.3B wan2.1_t2v_1_3b_nvfp4_lightx2v_4step
⚡ Performance Comparison

Test Environment : RTX 5090 Single GPU | LightX2V Framework

📸 Image-to-Video (I2V-14B-480P)
Metric Original Model Optimized Model Speedup
Single-step Denoising 12.10s 3.40s 3.5x
End-to-End 498.90s 17.65s 28x
🎬 Text-to-Video (T2V-1.3B-480P)
Metric Original Model Optimized Model Speedup
Single-step Denoising 2.00s 0.70s 2.9x
End-to-End 83.50s 6.54s 12.8x
⚠️ Notes
System Requirements
  • Required Hardware : NVIDIA RTX 50-series GPUs (RTX 5090/5080/5070/5060) or other Blackwell architecture GPUs
Dependencies
  • Prepare T5 / CLIP / VAE components yourself (same as Wan2.x structure)
Performance Tips
  • Use Blackwell + NVFP4 for best performance
  • Enable CPU offload for GPUs with limited memory
🤝 Community

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

Runs of lightx2v Wan-NVFP4 on huggingface.co

473
Total runs
0
24-hour runs
0
3-day runs
117
7-day runs
112
30-day runs

More Information About Wan-NVFP4 huggingface.co Model

More Wan-NVFP4 license Visit here:

https://choosealicense.com/licenses/apache-2.0

Wan-NVFP4 huggingface.co

Wan-NVFP4 huggingface.co is an AI model on huggingface.co that provides Wan-NVFP4's model effect (), which can be used instantly with this lightx2v Wan-NVFP4 model. huggingface.co supports a free trial of the Wan-NVFP4 model, and also provides paid use of the Wan-NVFP4. Support call Wan-NVFP4 model through api, including Node.js, Python, http.

lightx2v Wan-NVFP4 online free

Wan-NVFP4 huggingface.co is an online trial and call api platform, which integrates Wan-NVFP4's modeling effects, including api services, and provides a free online trial of Wan-NVFP4, you can try Wan-NVFP4 online for free by clicking the link below.

lightx2v Wan-NVFP4 online free url in huggingface.co:

https://huggingface.co/lightx2v/Wan-NVFP4

Wan-NVFP4 install

Wan-NVFP4 is an open source model from GitHub that offers a free installation service, and any user can find Wan-NVFP4 on GitHub to install. At the same time, huggingface.co provides the effect of Wan-NVFP4 install, users can directly use Wan-NVFP4 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Wan-NVFP4 install url in huggingface.co:

https://huggingface.co/lightx2v/Wan-NVFP4

Url of Wan-NVFP4

Wan-NVFP4 huggingface.co Url

Provider of Wan-NVFP4 huggingface.co

lightx2v
ORGANIZATIONS

Other API from lightx2v

huggingface.co

Total runs: 6.9K
Run Growth: -33
Growth Rate: -0.48%
Updated:2025年11月21日
huggingface.co

Total runs: 482
Run Growth: 30
Growth Rate: 6.22%
Updated:2025年12月28日