Z-Image ComfyUI Guide

Next-gen open-source image generation model based on S3-DiT architecture.
6B Params · 8-Step Turbo · Photorealistic

Recommended

Distilled version, optimized for speed and VRAM.

Non-distilled foundation model, base for community dev.

To be released

Dedicated editing model announced by Tongyi-MAI; its official weights have not been released yet.

Installation Guide

Ensure you have the latest ComfyUI. Download files from Hugging Face and place them as follows.

# Structure

ComfyUI/

├── models/

├── text_encoders/

└── qwen_3_4b.safetensors // Text Encoder

├── diffusion_models/

└── z_image_turbo_bf16.safetensors // Main Model (FP8/GGUF opt)

├── vae/

└── ae.safetensors // Flux 1 VAE

├── model_patches/

└── Z-Image-Turbo-Fun-Controlnet-Union.safetensors // (Optional) ControlNet

✓

Bilingual: Native support for Chinese prompts, excellent complex text rendering.

✓

Uncensored: Supports uncensored generation modes for high creative freedom.

✓

Ecosystem: Perfect support for ControlNet and LoRA extensions.

Turbo model needs NO negative prompts.

Add lighting keywords: "volumetric lighting", "cinematic lighting".

Be as specific as possible (scene, pose, texture).

Dedicated editing model announced by Tongyi-MAI; its official weights have not been released yet.