CivArchive
    Wan2.2-S2V-14B GGUF Q_3_K_M - VAE
    Preview 96843085

    Wan2.2 Speech to Video

    Base model: /ComfyUI/models/diffusion_models

    Audio Encoder: ComfyUI/models/audio_encoders/

    Text encoder: save it in: ComfyUI/models/text_encoders/

    VAE: (same as Wan2.1) ComfyUI/models/vae

    This is a Q3_K_M GGUF quantized version is ideal for systems with limited VRAM (under 10GB vram) or for users prioritizing faster inference over maximum accuracy.

    Description

    FAQ

    Comments (1)

    obcnob191Feb 14, 2026
    CivitAI

    sorry im stupid but were is the work flow?

    Checkpoint
    Wan Video 14B i2v 720p
    by civitai
    Download (Beta) View on CivitAI
    wan2.2 sound to video
    base model
    wan2.2 s2v

    Details

    Downloads
    155
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/27/2025
    Updated
    5/19/2026
    Deleted
    -

    Files

    wan22S2V14BGGUFQ3KM_vae.safetensors

    Size:
    242.06 MB
    SHA256:
    2fc39d31359a4b0a64f55876d8ff7fa8d780956ae2cb13463b0223e15148976b

    Mirrors

    HuggingFace (276 mirrors)
    CivitAI (4 mirrors)
    TensorFiles (1 mirrors)
    CivitasBay (1 mirrors)
    ModelScope (2 mirrors)
    ModelScope CN (4 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.

    SeaArt
    Wan2.2-S2V-14B GGUF Q_3_K_M - VAE