⚡️ Z-Image-Turbo
_{^{An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer}}

   

Welcome to the official repository for the Z-Image（造相）project!

✨ Z-Image

Z-Image is a powerful and highly efficient image generation model with 6B parameters. Currently there are three variants:

• 🚀 Z-Image-Turbo – A distilled version of Z-Image 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 comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence.

• 🧱 Z-Image-Base – The non-distilled foundation model. By releasing this checkpoint, we aim to unlock the full potential for community-driven fine-tuning and custom development.

• ✍️ Z-Image-Edit – A variant fine-tuned on Z-Image specifically for image editing tasks. It supports creative image-to-image generation with impressive instruction-following capabilities, allowing for precise edits based on natural language prompts.

🌟 Features

• ⚡️ Ultra-Fast Generation: Only 8 inference steps needed (sub-second on enterprise GPUs)
• 📸 Photorealistic Quality: Strong photorealistic image generation with excellent aesthetic quality
• 📖 Bilingual Text Rendering: Excels at rendering complex Chinese and English text
• 🎨 Advanced Architecture: Single-Stream Diffusion Transformer (S3-DiT) with Decoupled-DMD
• 🚀 Optimized Performance: Includes xformers and Flash Attention support

💾 Installation

1. Download the latest build from Releases
2. Extract the archive into any folder you prefer.
3. On Windows: run Zimage.exe to finalize setup.

🖼️ Showcase

📸 Photorealistic Quality: Z-Image-Turbo delivers strong photorealistic image generation while maintaining excellent aesthetic quality.

📖 Accurate Bilingual Text Rendering: Z-Image-Turbo excels at accurately rendering complex Chinese and English text.

💡 Prompt Enhancing & Reasoning: Prompt Enhancer empowers the model with reasoning capabilities, enabling it to transcend surface-level descriptions and tap into underlying world knowledge.

🧠 Creative Image Editing: Z-Image-Edit shows a strong understanding of bilingual editing instructions, enabling imaginative and flexible image transformations.

🏗️ Model Architecture

We adopt a Scalable Single-Stream DiT (S3-DiT) architecture. In this setup, text, visual semantic tokens, and image VAE tokens are concatenated at the sequence level to serve as a unified input stream, maximizing parameter efficiency compared to dual-stream approaches.

📈 Performance

According to the Elo-based Human Preference Evaluation (on Alibaba AI Arena), Z-Image-Turbo shows highly competitive performance against other leading models, while achieving state-of-the-art results among open-source models.

Click to view the full leaderboard

---