ComfyUI Workflow for Z Image
Any feedback would be appreciated.
📂 Required Models
Diffusion Model: z_image_turbo_bf16.safetensors .../ComfyUI/models/diffusion_models/
Text Encoder: qwen_3_4b.safetensors .../ComfyUI/models/text_encoders/
VAE: ae.safetensors .../ComfyUI/models/vae/
📂 Optional Models
Upscale Model: 4x_foolhardy_Remacri.pth .../ComfyUI/models/upscale_models
Detection Model: face_yolov9c.pt .../ComfyUI/models/ultralytics/bbox
SAM Model: sam_vit_b_01ec64.pth .../ComfyUI/models/sams
Fun-Controlnet-Union: Z-Image-Turbo-Fun-Controlnet-Union.safetensors .../ComfyUI/models/model_patches
https://huggingface.co/alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union/tree/main
Z Image Fun-Controlnet-Union requires the ComfyUI nightly version as of 3rd Dec. 2025
🧩 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-Impact-Pack (by ltdrdata)
https://github.com/ltdrdata/ComfyUI-Impact-Pack🟩 ComfyUI-Impact-Subpack (by ltdrdata)
https://github.com/ltdrdata/ComfyUI-Impact-Subpack🟪 ComfyUI-Image-Saver (by alexopus)
https://github.com/alexopus/ComfyUI-Image-Saver🟪 ComfyUI-Lora-Manager (by willmiao)
https://github.com/willmiao/ComfyUI-Lora-Manager🟪 ComfyUI-KJNodes (by kijai)
https://github.com/kijai/ComfyUI-KJNodes🟪 ComfyUI_essentials (by cubiq)
https://github.com/cubiq/ComfyUI_essentials
⚙️ 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] 640x1536Experiment and enjoy!

Description
Updated to V6.0
(This is not an exhaustive changelog)
Changes:
Fixes Improvements
Added Sage Attention Patch
Added simple LoRA Loader for basic version
FAQ
Comments (6)
Great advanced workflow. I looked through a lot of workflows and between the basics and the ultra-nerd-rocketships this is the best ive found for now.
I apologize if the machine translation made the meaning unclear.
The “Widget To String” function in ZImgGGUFV6.json was causing an error and stopping the process. I changed the ID to 107 since it was incorrect, or bypassed it, and it started working again.
I assume the ID you're specifying is for the Unet Loader, right?
Yes, that's correct. Thank you for pointing it out!
For those interested, there's also a GGUF version for the base model: https://huggingface.co/jayn7/Z-Image-GGUF/tree/main
You might wanna fix your noodles in V6. Either you mixed them up or some node parameters have changed since you made this, but denoise and scheduler are not connected properly. Thanks for the workflow!
How to fixed?













