Z-Image-GGUF
This is a GGUF quantized version of [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image). <br> unsloth/Z-Image-GGUF uses [Unsloth Dynamic 2.0](https://docs.unsloth.ai/basics/unsloth-dynamic-2.0-ggufs) methodology for SOTA performance. - Important layers are upcasted to higher precision. - Uses tooling from [ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) by city96. [](https://tongyi-mai.github.io/Z-Image-blog/)  [](https://github.com/Tongyi-MAI/Z-Image)  [](https://huggingface.co/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)  Welcome to the official repository for the Z-Image（造相）project! **Z-Image** is the foundation model of the ⚡️- Image family, engineered for good quality, robust generative diversity, broad stylistic coverage, and precise prompt adherence. While Z-Image-Turbo is built for speed, Z-Image is a full-capacity, undistilled transformer designed to be the backbone for creators, researchers, and developers who require the highest level of creative freedom. - **Undistilled Foundation**: As a non-distilled base model, Z-Image preserves the complete training signal. It supports full Classifier-Free Guidance (CFG), providing the precision required for complex prompt engineering and professional workflows. - **Aesthetic Versatility**: Z-Image masters a vast spectrum of visual languages—from hyper-realistic photography and cinematic digital art to intricate anime and stylized illustrations. It is the ideal engine for scenarios requiring rich, multi-dimensional expression. - **Enhanced Output Diversity**: Built for exploration, Z-Image delivers significantly higher variability in composition, facial identity, and lighting across different seeds, ensuring that multi-person scenes remain distinct and dynamic. - **Built for Development**: The ideal starting point for the community. Its non-distilled nature makes it a good base for LoRA training, structural conditioning (ControlNet) and semantic conditioning. - **Robust Negative Control**: Responds with high fidelity to negative prompting, allowing users to reliably suppress artifacts and adjust compositions. Install the latest version of diffusers: pip install git+https://github.com/huggingface/diffusers Download the model: pip install -U huggingface_hub HF_XET_HIGH_PERFORMANCE=1 hf download Tongyi-MAI/Z-Image - **Resolution:** 512×512 to 2048×2048 (total pixel area, any aspect ratio) - **Guidance scale:** 3.0 – 5.0 - **Inference steps:** 28 – 50 import torch from diffusers import ZImagePipeline pipe = ZImagePipeline.from_pretrained( "Tongyi-MAI/Z-Image", torch_dtype=torch.bfloat16, low_cpu_mem_usage=False, ) pipe.to("cuda") prompt = "两名年轻亚裔女性紧密站在一起，背景为朴素的灰色纹理墙面，可能是室内地毯地面。左侧女性留着长卷发，身穿藏青色毛衣，左袖有奶油色褶皱装饰，内搭白色立领衬衫，下身白色裤子；佩戴小巧金色耳钉，双臂交叉于背后。右侧女性留直肩长发，身穿奶油色卫衣，胸前印有“Tun the tables”字样，下方为“New ideas”，搭配白色裤子；佩戴银色小环耳环，双臂交叉于胸前。两人均面带微笑直视镜头。照片，自然光照明，柔和阴影，以藏青、奶油白为主的中性色调，休闲时尚摄影，中等景深，面部和上半身对焦清晰，姿态放松，表情友好，室内环境，地毯地面，纯色背景。" negative_prompt = "" # Optional, but would be powerful when you want to remove some unwanted content image = pipe( prompt=prompt, negative_prompt=negative_prompt, height=1280, width=720, cfg_normalization=False, num_inference_steps=50, guidance_scale=4, generator=torch.Generator("cuda").manual_seed(42), ).images[0] image.save("example.png") If you find our work useful in your research, please consider citing: @article{team2025zimage, title={Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer}, author={Z-Image Team}, journal={arXiv preprint arXiv:2511.22699}, year={2025} }