Z Image

<h1 align="center">⚡️- Image<br>_{^{An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer}}</h1> <div align="center">

                      <a href="https://arxiv.org/abs/2511.22699" target="_blank"><img src="https://img.shields.io/badge/Report-b5212f.svg?logo=arxiv" height="21px"></a>

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

</div>

✨ Z-Image

Z-Image is a powerful and highly efficient image generation model family with 6B parameters. Currently there are four 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 – The foundation model behind Z-Image-Turbo. Z-Image focuses on high-quality generation, rich aesthetics, strong diversity, and controllability, well-suited for creative generation, fine-tuning, and downstream development. It supports a wide range of artistic styles, effective negative prompting, and high diversity across identities, poses, compositions, and layouts.

• 🧱 Z-Image-Omni-Base – The versatile foundation model capable of both generation and editing tasks. By releasing this checkpoint, we aim to unlock the full potential for community-driven fine-tuning and custom development, providing the most "raw" and diverse starting point for the open-source community.

• ✍️ 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.

📣 News

• [2026-01-27] 🔥 Z-Image is released! We have released the model checkpoint on Hugging Face and ModelScope. Try our online demo!
• [2025-12-08] 🏆 Z-Image-Turbo ranked 8th overall on the Artificial Analysis Text-to-Image Leaderboard, making it the 🥇 <strong style="color: #FFC300;">#1 open-source model</strong>! Check out the full leaderboard.
• [2025-12-01] 🎉 Our technical report for Z-Image is now available on arXiv.
• [2025-11-26] 🔥 Z-Image-Turbo is released! We have released the model checkpoint on Hugging Face and ModelScope. Try our online demo!

📥 Model Zoo

| Model | Pre-Training | SFT | RL | Step | CFG | Task | Visual Quality | Diversity | Fine-Tunability | Hugging Face | ModelScope | | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | Z-Image-Omni-Base | ✅ | ❌ | ❌ | 50 | ✅ | Gen. / Editing | Medium | High | Easy | To be released | To be released | | Z-Image | ✅ | ✅ | ❌ | 50 | ✅ | Gen. | High | Medium | Easy | <br> | <br> | | Z-Image-Turbo | ✅ | ✅ | ✅ | 8 | ❌ | Gen. | Very High | Low | N/A | <br> | <br> | | Z-Image-Edit | ✅ | ✅ | ❌ | 50 | ✅ | Editing | High | Medium | Easy | To be released | To be released |

The figure below illustrates at which training stage each model is produced.

🖼️ 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

Z-Image-Turbo's performance has been validated on multiple independent benchmarks, where it consistently demonstrates state-of-the-art results, especially as the leading open-source model.

Artificial Analysis Text-to-Image Leaderboard

On the highly competitive Artificial Analysis Leaderboard, Z-Image-Turbo ranked 8th overall and secured the top position as the 🥇 <strong style="color: gold;">#1 Open-Source Model</strong>, outperforming all other open-source alternatives.

<p align="center"> <a href="https://artificialanalysis.ai/image/leaderboard/text-to-image"> <img src="assets/image_arena_all.jpg" alt="Z-Image Rank on Artificial Analysis Leaderboard"/><br /> <span style="font-size:1.05em; cursor:pointer; text-decoration:underline;"> Artificial Analysis Leaderboard</span> </a> </p> <p align="center"> <a href="https://artificialanalysis.ai/image/leaderboard/text-to-image"> <img src="assets/image_arena_os.jpg" alt="Z-Image Rank on Artificial Analysis Leaderboard (Open-Source Model Only)"/><br /> <span style="font-size:1.05em; cursor:pointer; text-decoration:underline;"> Artificial Analysis Leaderboard (Open-Source Model Only)</span> </a> </p>

Alibaba AI Arena Text-to-Image Leaderboard

According to the Elo-based Human Preference Evaluation on [Alibaba AI Arena](https://aiarena.alibaba-inc.com/corpora/