Z-Image (造相) is a powerful and highly efficient image generation model with 6B parameters, developed by Alibaba’s Tongyi Lab. It uses a Scalable Single-Stream DiT (S3-DiT) architecture where text, visual semantic tokens, and image VAE tokens are concatenated at the sequence level to serve as a unified input stream, maximizing parameter efficiency.
Model Variants:
- 🚀 Z-Image-Turbo – A distilled version that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits within 16GB VRAM consumer devices.
- 🧱 Z-Image-Base – The non-distilled foundation model for community-driven fine-tuning and custom development.
- ✍️ Z-Image-Edit – A variant fine-tuned for image editing tasks with impressive instruction-following capabilities.
Model Highlights:
- Photorealistic Quality: Delivers strong photorealistic image generation while maintaining excellent aesthetic quality
- Accurate Bilingual Text Rendering: Excels at accurately rendering complex Chinese and English text
- Prompt Enhancing & Reasoning: Prompt Enhancer empowers the model with reasoning capabilities
- Sub-second Inference: Achieves fast generation speed on supported hardware
Related Links:
Z-Image-Turbo text-to-image workflow
Download JSON Workflow File
Run on ComfyUI Cloud
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates.
If you can’t find them in the template, your ComfyUI may be outdated. (Desktop version’s update will delay sometime)If nodes are missing when loading a workflow, possible reasons:
- You are not using the latest ComfyUI version (Nightly version)
- Some nodes failed to import at startup
Model links
text_encoders
diffusion_models
vae
Model Storage Location
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 text_encoders/
│ │ └── qwen_3_4b.safetensors
│ ├── 📂 diffusion_models/
│ │ └── z_image_turbo_bf16.safetensors
│ └── 📂 vae/
│ └── ae.safetensors
