Sign In

Wan2.1 I2V Lightx2v Step/CFG NVFP4

Download

1 variant available

nf4 Other

4-bit normalized • 10.09 GB

Verified:

You need these files to run this model. We'll show the best match for your preferences.

VAE

wan_2.1_vae.safetensors242.06 MB

Verified:

CLIP Vision

clip_vision_h.safetensors1.18 GB

Verified:

Downloads your preferred variants

Type

Checkpoint

Stats

0

Reviews

No reviews yet

Published

Apr 23, 2026

Base Model

Wan Video 14B i2v 480p

Hash

AutoV2
64A7EF761B

License:

Apache 2.0

This is a partial NVFP4 quantization of Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v by lightx2v, produced using convert_to_quant by silveroxides.

Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v is an image-to-video generation model built on Wan2.1-I2V-14B-480P. It applies step distillation and classifier-free guidance distillation to reduce inference to 4 steps without CFG, cutting generation time substantially while preserving output quality.

IMPORTANT

Since NVFP4 is only supported on NVIDIA Blackwell architecture GPUs, running this model requires a Blackwell GPU with its corresponding support enabled in torch, along with a recent version of ComfyUI and comfy-kitchen built against CUDA 13.

The model can be used in ComfyUI with the following parameters, based on the distilled model's own recommendations:

  • Shift: 5.0

  • Sampler: LCM

  • Scheduler normal

  • CFG: 1.0

  • Steps: 4

Other combinations are possible, such as euler/simple and heun/linear_quadratic.