Z-Image

⚡️- Image
An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

## ✨ 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](https://huggingface.co/Tongyi-MAI/Z-Image) and [ModelScope](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image). Try our [online demo](https://www.modelscope.cn/aigc/imageGeneration?tab=advanced&versionId=569345&modelType=Checkpoint&sdVersion=Z_IMAGE&modelUrl=modelscope%3A%2F%2FTongyi-MAI%2FZ-Image%3Frevision%3Dmaster)! * **[2025-12-08]** Z-Image-Turbo ranked 8th overall on the **Artificial Analysis Text-to-Image Leaderboard**, making it the #1 open-source model! [Check out the full leaderboard](https://artificialanalysis.ai/image/leaderboard/text-to-image). * **[2025-12-01]** Our technical report for Z-Image is now available on [arXiv](https://arxiv.org/abs/2511.22699). * **[2025-11-26]** **Z-Image-Turbo is released!** We have released the model checkpoint on [Hugging Face](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo) and [ModelScope](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo). Try our [online demo](https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo)! ### 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 | [](https://huggingface.co/Tongyi-MAI/Z-Image)
[](https://huggingface.co/spaces/Tongyi-MAI/Z-Image) | [](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image)
[](https://www.modelscope.cn/aigc/imageGeneration?tab=advanced&versionId=569345&modelType=Checkpoint&sdVersion=Z_IMAGE&modelUrl=modelscope%3A%2F%2FTongyi-MAI%2FZ-Image%3Frevision%3Dmaster) | | **Z-Image-Turbo** | ✅ | ✅ | ✅ | 8 | ❌ | Gen. | Very High | Low | N/A | [](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo)
[](https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo) | [](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo)
[](https://www.modelscope.cn/aigc/imageGeneration?tab=advanced&versionId=469191&modelType=Checkpoint&sdVersion=Z_IMAGE_TURBO&modelUrl=modelscope%3A%2F%2FTongyi-MAI%2FZ-Image-Turbo%3Frevision%3Dmaster) | | **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](https://artificialanalysis.ai/image/leaderboard/text-to-image), Z-Image-Turbo ranked **8th overall** and secured the top position as the #1 Open-Source Model, outperforming all other open-source alternatives.

Artificial Analysis Leaderboard

Artificial Analysis Leaderboard (Open-Source Model Only)

#### 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/arena/leaderboard?arenaType=T2I), Z-Image-Turbo also achieves state-of-the-art results among open-source models and shows highly competitive performance against leading proprietary models.

Alibaba AI Arena Text-to-Image Leaderboard

### Quick Start #### (1) PyTorch Native Inference Build a virtual environment you like and then install the dependencies: ```bash pip install -e . ``` Then run the following code to generate an image: ```bash python inference.py ``` #### (2) Diffusers Inference Install the latest version of diffusers, use the following command: Click here for details for why you need to install diffusers from source We have submitted two pull requests ([#12703](https://github.com/huggingface/diffusers/pull/12703) and [#12715](https://github.com/huggingface/diffusers/pull/12715)) to the diffusers repository to add support for Z-Image. Both PRs have been merged into the latest official diffusers release. Therefore, you need to install diffusers from source for the latest features and Z-Image support. ```bash pip install git+https://github.com/huggingface/diffusers ``` Z-Image-Turbo - Click to expand Then, try the following code to generate an image: ``` … ``` Z-Image - Click to expand Recommended Parameters: - **Resolution:** 512×512 to 2048×2048 (total pixel area, any aspect ratio) - **Guidance scale:** 3.0 – 5.0 - **Inference steps:** 28 – 50 - **Negative prompts:** Strongly recommended for better control - **CFG normalization:** `False` for general stylism, `True` for realism Then, try the following code to generate an image: ``` … ``` ## Decoupled-DMD: The Acceleration Magic Behind Z-Image Decoupled-DMD is the core few-step distillation algorithm that empowers the 8-step Z-Image model. Our core insight in Decoupled-DMD is that the success of existing DMD (Distribution Matching Distillation) methods is the result of two independent, collaborating mechanisms: - **CFG Augmentation (CA)**: The primary **engine** driving the distillation process, a factor largely overlooked in previous work. - **Distribution Matching (DM)**: Acts more as a **regularizer** ⚖️, ensuring the stability and quality of the generated output. By recognizing and decoupling these two mechanisms, we were able to study and optimize them in isolation. This ultimately motivated us to develop an improved distillation process that significantly enhances the performance of few-step generation. ## DMDR: Fusing DMD with Reinforcement Learning Building upon the strong foundation of Decoupled-DMD, our 8-step Z-Image model has already demonstrated exceptional capabilities. To achieve further improvements in terms of semantic alignment, aesthetic quality, and structural coherence—while producing images with richer high-frequency details—we present **DMDR**. Our core insight behind DMDR is that Reinforcement Learning (RL) and Distribution Matching Distillation (DMD) can be synergistically integrated during the post-training of few-step models. We demonstrate that: - **RL Unlocks the Performance of DMD** - **DMD Effectively Regularizes RL** ⚖️ ## Community Works - [Cache-DiT](https://github.com/vipshop/cache-dit) provides inference acceleration for **Z-Image** and **Z-Image-ControlNet** via DBCache, Context Parallelism and Tensor Parallelism. It achieves nearly **4x** speedup on 4 GPUs with negligible precision loss. Please visit their [example](https://github.com/vipshop/cache-dit/blob/main/examples) for more details. - [stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp) is a pure C++ diffusion model inference engine that supports fast and memory-efficient Z-Image inference across multiple platforms (CUDA, Vulkan, etc.). You can use stable-diffusion.cpp to generate images with Z-Image on machines with as little as **4GB** of VRAM. For more information, please refer to [How to Use Z‐Image on a GPU with Only 4GB VRAM](https://github.com/leejet/stable-diffusion.cpp/wiki/How-to-Use-Z%E2%80%90Image-on-a-GPU-with-Only-4GB-VRAM). - [stable-diffusion.cpp](https://github.com/leejet/stable-diffusion.cpp) is a pure C++ diffusion model inference engine that supports fast and memory-efficient Z-Image inference across multiple platforms (CUDA, Vulkan, etc.). You can use stable-diffusion.cpp to generate images with Z-Image on machines with as little as **4GB** of VRAM. For more information, please refer to [How to Use Z‐Image on a GPU with Only 4GB VRAM](https://github.com/leejet/stable-diffusion.cpp/wiki/How-to-Use-Z%E2%80%90Image-on-a-GPU-with-Only-4GB-VRAM). - [LeMiCa](https://github.com/UnicomAI/LeMiCa) provides a training-free, timestep-level acceleration method that conveniently speeds up Z-Image inference. For more details, see [LeMiCa4Z-Image](https://github.com/UnicomAI/LeMiCa/tree/main/LeMiCa4Z-Image). - [ComfyUI ZImageLatent](https://github.com/HellerCommaA/ComfyUI-ZImageLatent) provdes an easy to use latent of the official Z-Image resolutions. - [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) has provided more support for Z-Image, including LoRA training, full training, distillation trai