CivArchive
    Z Image (Turbo & Base) Workflow - V3.0
    NSFW
    Preview 112584767
    Preview 112584776
    Preview 112584828
    Preview 112584829
    Preview 112584827
    Preview 112584825
    Preview 112588481
    Preview 112588474
    Preview 112588488
    Preview 112588479
    Preview 112588487
    Preview 112588482
    Preview 112588472
    Preview 112588478
    Preview 112588537
    Preview 112588536
    Preview 112588540
    Preview 112588541
    Preview 112602525
    Preview 112602521

    ComfyUI Workflow for Z Image


    Any feedback would be appreciated.


    📂 Required Models

    1. Diffusion Model: z_image_turbo_bf16.safetensors .../ComfyUI/models/diffusion_models/

    2. Text Encoder: qwen_3_4b.safetensors .../ComfyUI/models/text_encoders/

    3. VAE: ae.safetensors .../ComfyUI/models/vae/

    📂 Optional Models


    🧩 Required Custom Nodes


    • Turbo Steps: 6 to 10 (Default set to 9).

    • Turbo CFG: 1.0 (Default set to 1.0).

    • Base Steps: 25 to 50

    • Base CFG: 3.0 to 6.0

    • Sampler: euler or res_multistep

    • Scheduler: simple

    [1:1] 1024x1024
    [3:4] 896x1152
    [5:8] 832x1216
    [9:16] 768x1344
    [9:21] 640x1536

    Experiment and enjoy!


    Description

    Updated to V3.0

    (This is not an exhaustive changelog)

    General:

    • Fixes and Improvements

    GGUF Versions:

    • Added GGUF Version of the Workflows

    LoRA Versions:

    • Added Fun ControlNet Union support instead of just loading an image

    Workflows
    ZImageTurbo

    Details

    Downloads
    778
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/7/2025
    Updated
    3/9/2026
    Deleted
    -

    Files

    zImageTurboBase_v30.zip

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)