ComfyUI Workflow for Z Image Turbo

Any feedback would be appreciated.

📂 Required Models

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

   • https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/diffusion_models

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

   • https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/text_encoders

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

   • https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/vae

📂 Optional Models

• Upscale Model: 4x_foolhardy_Remacri.pth .../ComfyUI/models/upscale_models

  • https://huggingface.co/FacehugmanIII/4x_foolhardy_Remacri

• Detection Model: face_yolov9c.pt .../ComfyUI/models/ultralytics/bbox

  • https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt

• SAM Model: sam_vit_b_01ec64.pth .../ComfyUI/models/sams

  • https://github.com/facebookresearch/segment-anything#model-checkpoints

🧩 Required Custom Nodes

• 🟩 ComfyUI-Manager (by Comfy-Org)
  https://github.com/Comfy-Org/ComfyUI-Manager

• 🟩 rgthree-comfy (by rgthree)
  https://github.com/rgthree/rgthree-comfy

• 🟩 ComfyUI-Easy-Use (by yolain)
  https://github.com/yolain/ComfyUI-Easy-Use

• 🟩 ComfyUI-Image-Saver (by alexopus)
  https://github.com/alexopus/ComfyUI-Image-Saver

• 🟩 ComfyUI-Impact-Pack (by ltdrdata)
  https://github.com/ltdrdata/ComfyUI-Impact-Pack

• 🟩 ComfyUI-Impact-Subpack (by ltdrdata)
  https://github.com/ltdrdata/ComfyUI-Impact-Subpack

• 🟪 ComfyUI-Lora-Manager (by willmiao)
  https://github.com/willmiao/ComfyUI-Lora-Manager

⚙️ Recommended Settings

• Steps: 4 to 10 (Default set to 9).

• CFG: 1.0 to 2.0 (Default set to 1.0).

• Sampler: Euler

• Scheduler: Simple

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

Experiment and enjoy!