CivArchive
    Z-Image Trained Text Encoder - FP32
    NSFW
    Preview 121249512
    Preview 121249513
    Preview 121250280
    Preview 121255923
    Preview 121255925
    Preview 121256718
    Preview 121257383
    Preview 121257717
    Preview 121258449
    Preview 121259491
    Preview 121261026
    Preview 121261143
    Preview 121261532
    Preview 121261597
    Preview 121261891
    Preview 121263502
    Preview 121729588
    Preview 121729587
    Preview 121729584
    Preview 121729589

    Qwen 3_4_B Trained Text Encoder for Z-Image

    FP32

    • Full Finetune at FP32 (Full Model Finetune - All Parameters & All layers)

    • FP32 Finetune of QWEN3_4b focusing on describing human features SFW/NSFW captions.

    • Can be run in FP32 with no time loss on most machines that use CPU offloading.

    BF16

    • Full Finetune at BF16 (20 Layers)

    • Long Text descriptions 500-1000 token length focusing on describing human features.

    • For use with Z-Image or Z-Image Turbo

    • Comparison Images showing QWEN base VS Human Corpus HERE

    Description

    FAQ

    Checkpoint
    ZImageTurbo
    by Felldude
    Download (Beta) View on CivitAI
    z-image-turbo
    z-image
    qwen3_4_b
    qwen3
    base model
    human
    te

    Details

    Downloads
    992
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/16/2026
    Updated
    4/26/2026
    Deleted
    -

    Files

    zImageTrainedText_fp32.safetensors

    Size:
    14.98 GB
    SHA256:
    43c96d1b7dbb218c885c9a65afd94b91f61bc553a91cdf64fff38ddf4346a986

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)