<a target="_blank" rel="ugc" href="https://civarchive.com/models/2168935?modelVersionId=2442540">Text Encoder</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/2168935?modelVersionId=2442479">VAE</a><a target="_blank" rel="ugc" href="https://github.com/ostris/ai-toolkit/">Early support for LoRA training (Turbo)</a> | <a rel="ugc" href="https://civarchive.com/articles/23015/z-image-studio">Prompt Guide</a>If you're already using SDXL, Flux, or Qwen-based generators, here's the simple version of what Z-Image-Turbo is:It's a super-fast text-to-image model from Alibaba that spits out 1024×1024 pictures in less than a second on a single high-end card (or a couple of seconds on a 3090/4090). Speed comes from heavy distillation , it’s basically a 6B model taught by much bigger internal beasts, so it feels closer to closed top-tier models than most open-source stuff.Compared to what you know:<ul><li>Faster than Flux and SDXL (the SD3.5 Turbo is a bit faster in my testing.)</li><li>Better prompt following and prettier results than most current open models</li><li>Renders English and Chinese text in images almost perfectly</li><li>Currently sitting at #1 on the public human-voted leaderboard (AI Arena Elo)</li></ul>Tongyi-MAI <a target="_blank" rel="ugc" href="https://huggingface.co/Tongyi-MAI/Z-Image-Turbo">HF</a> | <a target="_blank" rel="ugc" href="https://github.com/Tongyi-MAI/Z-Image">GitHub</a>The model is mirrored here for convenience.

Files with SHA256: 20e8de9a7b8322a359266f2b07238c25919d988df293081021ca09bd31511af2