CivArchive
    Wan2.1 I2V Lightx2v Step/CFG NVFP4 - v1.0
    NSFW

    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.

    Description

    This version tries to protect the following layers, among others.

    • cross_attn.k

    • cross_attn.q

    • self_attn.k

    • self_attn.q

    Checkpoint
    Wan Video 14B i2v 480p

    Details

    Downloads
    0
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/23/2026
    Updated
    4/27/2026
    Deleted
    -

    Files

    wan21I2VLightx2vStep_v10.safetensors

    Mirrors

    wan21I2VLightx2vStep_v10.safetensors

    Mirrors