CivArchive
    Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1 - Seko_lora_high noise
    Preview 113967059

    Wan2.2-Lightning by lightx2v

    Just uploading this here because I didn't see it on civitai. It's NOT made by me it's made by the amazing lightx2v team. I just downloaded from huggingface and uploaded it for use here.

    We are excited to release the distilled version of Wan2.2 video generation model family, which offers the following advantages:

    • Fast: Video generation now requires only 4 steps without the need of CFG trick, leading to x20 speed-up

    • High-quality: The distilled model delivers visuals on par with the base model in most scenarios, sometimes even better.

    • Complex Motion Generation: Despite the reduction to just 4 steps, the model retains excellent motion dynamics in the generated scenes.

    Description

    FAQ

    Comments (3)

    crafted101Dec 16, 2025
    CivitAI

    thank you works great better then what i was using no longer have melting skin thanks for sharing

    TompteDec 16, 2025· 6 reactions
    CivitAI

    *angrily renames files* (Thank you!)

    stockingsgarry579Dec 16, 2025
    CivitAI

    True, it was missing here, but very important LORA. Thx!

    LORA
    Wan Video 2.2 I2V-A14B
    by undopandu
    Download (Beta) View on CivitAI
    style

    Details

    Downloads
    944
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/15/2025
    Updated
    5/13/2026
    Deleted
    -

    Files

    high_noise_model.safetensors

    Size:
    1.14 GB
    SHA256:
    d176c808d6fc461999b68e321efcb7501b20b8c3797523ed0df14f7d1deff11e

    Mirrors

    HuggingFace (158 mirrors)
    CivitAI (2 mirrors)
    ModelScope CN (3 mirrors)
    TensorArt (1 mirrors)