CivArchive
    Bernini GGUF - v1.0
    NSFW


    UPDATE TO THE LATEST COMFY!

    Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

    On video editing, Bernini reaches the first tier among leading closed-source commercial models.



    HIGH and LOW Diffusion Model (REQUIRES BOTH MODELS)

    https://huggingface.co/neuregex/Bernini-R-GGUF/tree/main

    Text Encoder

    https://huggingface.co/Osrivers/umt5_xxl_fp8_e4m3fn_scaled.safetensors/tree/main

    VAE
    https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main/VAE

    LoRA (REQUIRED FOR DISTILLATION STEP COUNT)
    https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill-Lightx2v/tree/main/loras

    Description

    bernini i2v

    FAQ

    Comments (4)

    minanimator28Jun 9, 2026
    CivitAI

    tried my 3rd gen, im getting no outputs in the comfyui(it renders but doesnt show an output), after checking folder output i got a bad noise output only, am i missing something pls help!

    iamgregorJun 19, 2026
    CivitAI

    I saw this on your youtube in the comments and I got the same thing. No idea why

    - Exception Message: RuntimeError: Boolean value of Tensor with more than one value is ambiguous

    Neo_fernuzJun 23, 2026

    is the bernini conditioning node, add it manually, that should fix it

    realrebelai
    Author
    Jun 23, 2026

    yeah i think yours was just bugged out, re add to workflow

    Workflows
    Wan Video 2.2 I2V-A14B

    Details

    Downloads
    749
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/2/2026
    Updated
    6/30/2026
    Deleted
    -

    Files

    berniniGGUF_v10.zip

    Mirrors

    CivitAI (1 mirrors)