CivArchive
    Picturd style | [MOSS | Krea2 | Z-Image-Turbo] - z-t-v1.0
    NSFW
    Preview 115227316
    Preview 115227317
    Preview 115227311
    Preview 115227310
    Preview 115227309
    Preview 115227314
    Preview 115227315
    Preview 115227312
    Preview 115227313
    Preview 115233599

    LoRA for MOSS / Krea2 / Z-Image generating in the style of artist Picturd.

    MOSS

    Trained on MOSS-Image-SFT

    Examples made on default comfy workflow with PiD upscaler.

    er_sde + simple, 50 steps, cfg 3, lora strength 1. Resolution - 2 mpx on multiple of 16.

    Stating the obvious - to render in this style you need it to be illustration, 2d, anime, etc.
    Tl:dr do not use it with realistic description if your goal is to emulate this style

    Krea 2

    Trained on Krea 2 raw, tested on raw with turbo lora.

    Examples made on 12 steps + euler + simple + PiD, lora strength 0.8 - 1, recommended is 0.9

    Workflows are imbedded in the images.

    ZIT

    Works with strength between 0.7-1, 1 can be glitchy depending on complexity of the prompt.

    All of examples are made in 0.9-1 and tiled upscaler - euler_a+simple 12 steps.
    Workflows are imbedded in the pics.

    Fist LoRA trying 2d/cartoon/anime image training, still experimenting with params.

    Description

    FAQ

    LORA
    ZImageTurbo

    Details

    Downloads
    223
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/26/2025
    Updated
    10/28/2026
    Deleted
    -

    Files

    picturd-z-t.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)