CivArchive
    Speed Core V1 6-10 steps - v2.0 BF16
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Settings:
    V1:Euler, simple, cfg 1-1.5 (2 can become blurry), steps 6-10.
    V2:Euler, simple, cfg 1-1.5, steps 4-10.

    Interesting negative I sometimes like to try: perfect symmetric face,
    Uses the new 4 and 8 step loras from https://huggingface.co/alibaba-pai/Z-Image-Fun-Lora-Distill/tree/main combined, plus my big lora.

    Description

    sharper, less seedreamy, can work decent at 4 steps

    FAQ

    Comments (12)

    CupRunethOverWithLSDFeb 13, 2026· 2 reactions
    CivitAI

    Can you please, please, please tell me how you created a Q8 from a ZIB model? All the methods I've used so far (City96, llama.cpp, ModelQuantizer node) fail with ZIB and Flux.2 Klein. The internet, Gemini, ChatGPT, etc. don't know the answer either and all give the same answers, none of which work.

    TiwazM
    Author
    Feb 13, 2026

    the city96 tools work you might just have to use a newer branch like this one https://github.com/city96/ComfyUI-GGUF/tree/auto_convert

    ferretduckFeb 13, 2026· 1 reaction

    ggufy can convert lumina2 based models as well, including z-image turbo or base (disclaimer: I made this tool) https://github.com/qskousen/ggufy

    @ferretduck Yeaaaah, thank you for your work! I will try it! Also Flux?

    Edit: Linux and Windows only, I'll have to see if I can get it to run on MacOS somehow...
    Edit 2: Unfortunately not. Tried to compile ggml-alloc.c (classic ggml allocator file), but it is missing from the vendor/ggml/src/ folder of the repository → FileNotFound → CacheCheckFailed.

    TiwazM
    Author
    Feb 13, 2026

    @ferretduck nice I will have a look sometime

    ferretduckFeb 13, 2026

    @heinerheinervonvielen417 sorry about that! I don't have a mac at the moment so I am unable to debug this currently.

    @ferretduck No problem, maybe the default ggml-alloc.c File will work…?!

    ferretduckFeb 13, 2026

    @heinerheinervonvielen417 I'll try to debug this in the next few days as I have time.

    @ferretduck I'm happy to help you if I can.

    ferretduckFeb 13, 2026

    @heinerheinervonvielen417 I've DM'd you so we can continue this somewhere other than this model's comment section, haha.

    ferretduckFeb 13, 2026

    just in case anyone read this and wondered -- ggufy now works on MacOS, both arm64 (apple silicon, M-series) and x86_64 (intel)! thanks @heinerheinervonvielen417 for the help testing those!

    CupRunethOverWithLSDFeb 14, 2026· 1 reaction

    @ferretduck This tool, ladies and gentlemen, is the fastest and easiest tool you will find! It was my pleasure to help!

    Checkpoint
    ZImageBase

    Details

    Downloads
    184
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/13/2026
    Updated
    5/15/2026
    Deleted
    -

    Files

    speedCoreV1610Steps_v20BF16.safetensors

    Mirrors