ComfyUI Workflow for Z Image

Any feedback would be appreciated.

📂 Required Models

Diffusion Model: z_image_turbo_bf16.safetensors .../ComfyUI/models/diffusion_models/
- />GGUF Variants:
- />Base model:
- Encoder: qwen_3_4b.safetensors .../ComfyUI/models/text_encoders/
  - />GGUF Variants:
  - ae.safetensors .../ComfyUI/models/vae/
    - id="optional-models">📂 Optional Models
      - Upscale Model: 4x_foolhardy_Remacri.pth .../ComfyUI/models/upscale_models
        Model: face_yolov9c.pt .../ComfyUI/models/ultralytics/bbox
        Model: sam_vit_b_01ec64.pth .../ComfyUI/models/sams
        Z-Image-Turbo-Fun-Controlnet-Union.safetensors .../ComfyUI/models/model_patches
        />Z Image Fun-Controlnet-Union requires the ComfyUI nightly version as of 3rd Dec. 2025
        🧩 Required Custom Nodes
        🟩 ComfyUI-Manager (by Comfy-Org)
        rgthree-comfy (by rgthree)
        style="color:rgb(34, 139, 230)"> ComfyUI-Easy-Use (by yolain)
        ComfyUI-Impact-Pack (by ltdrdata)
        style="color:rgb(34, 139, 230)"> ComfyUI-Impact-Subpack (by ltdrdata)
        ComfyUI-Image-Saver (by alexopus)
        ComfyUI-Lora-Manager (by willmiao)
        ComfyUI-KJNodes (by kijai)
        ComfyUI_essentials (by cubiq)
        />
        ⚙️ Recommended Settings
        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!

Model Info

Download Model