Important: if you have ModelPatchLoader error you should update your ComfyUI to nightly version!

NEW alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.0 is available with better quality and inpaint/outpaint support — click for more details and download. Waiting for ComfyUI support (there is an error now)

Welcome to my 💫🌄 Friendly Z-Image-Turbo ControlNet!

✨ Less mess, more magic

Would you like to see Inpaint version of ControlNet?

Z-Image-Turbo - everyone already knows it's overkill!) And now this is the ControlNet and everything is possible!

Choose one of five ControlNet modes or use them together at once: Canny, Depth, Openpose, HED, MLSD.

🚀 Z-Image-Turbo has a speed and quality balance advantage over other local models such as Flux 1, Flux 2, Qwen and others!

Generate 2048 x 2048 images even with 6GB VRAM!

I offer my workflow, with which you can generate on a full BF16 model without sacrificing quality and at the same speed. This requires at least 6GB of video memory and at least 32GB of RAM. No Tritons or SageAttention! Simply configure the required amount of video memory dumped to RAM in the "VRAM Optimizer+" node (MultiGPU node is required).

The latest version of ComfyUI is required.

💻 System requirements:

• Minimum system requirements:

RTX 3000-s, 6GB VRAM, 32GB+ RAM, 8-core processor, SSD, latest ComfyUI

📌 Detailed tips and links to models in the workflow

✨ Workflow features:

• Extremely user-friendly interface

• Maximum performance even on low-end systems with at least 6GB of VRAM

• Enchance details parameter

• Support for 5 ControlNet models

• Support for up to 3 Lora

• Detailed tooltips, including recommended samplers for best quality

• Manual random seed for complete control over generations

🤗🙏🏼 Thanks to Tongyi-MAI

Original repo — GitHub