CivArchive
    Krea 2 [w4a8] - turbo (w4a8)
    NSFW
    Preview 139095147

    Converted from https://huggingface.co/Comfy-Org/Krea-2/tree/main/diffusion_models

    All credit belongs to the original model author. License is the same as the original model.

    Quantized qwen3vl text encoder: link.


    This quantized ckpt uses mixed precision. Instead of quantizing the entire model to targeted format. This ckpt keeps important layers in high precision for better quality. (Similar to M and XL suffixes in GGUF)

    All txtfusion layers are in high precision. You don't needs to worry the precision when applying "Refusal-Reduction" LoRA (or whatever new LoRAs that try to nuke the txtfusion layers and the safety filter).


    Scaled fp8 and nvfp4 are deprecated.

    Use int8convrot or w4a8 instead. Faster, higher precision.

    Description

    FAQ

    Comments (3)

    plkAug 8, 2026
    CivitAI

    FYI I'm pretty sure Forge also supports INT4 now too.

    delta45424155Aug 8, 2026
    CivitAI

    Could you do the same for raw?

    Checkpoint
    Krea 2

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    410
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    8/8/2026
    Updated
    9/26/2026
    Deleted
    9/26/2026

    Files

    krea2W4a8_turboW4a8.safetensors

    Mirrors