{
 "slug": "z-image-turbo",
 "name": "Z-Image-Turbo",
 "author": "Tongyi-MAI",
 "density": "full",
 "status": "active",
 "status_note": null,
 "alternatives_page": null,
 "one_liner": "Efficient open-weights image generation model built on a single-stream diffusion transformer.",
 "category": {
  "slug": "ai-images",
  "name": "AI image generators"
 },
 "tags": [
  "Open source"
 ],
 "styles": [],
 "logo_url": "https://agentgid.com/media/avatars/tongyi-mai.png",
 "logo_letter": "Z",
 "links": {
  "repo": "https://github.com/Tongyi-MAI/Z-Image",
  "website": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo",
  "api_docs": null
 },
 "preview": null,
 "verdicts": [
  {
   "key": "price",
   "label": "Price",
   "value": "Free",
   "status": "yes",
   "sub": "No paid plan",
   "quote": null,
   "note": "Open weights, free to download; self-hosted.",
   "source": {
    "label": "huggingface.co/Tongyi-MAI/Z-Image-Turbo",
    "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo"
   },
   "n": 1
  },
  {
   "key": "commercial",
   "label": "Commercial use",
   "value": "Yes",
   "status": "yes",
   "sub": "Apache-2.0",
   "quote": "license: apache-2.0",
   "note": "Apache-2.0 allows commercial use of the model.",
   "source": {
    "label": "huggingface.co",
    "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/README.md"
   },
   "n": 2
  },
  {
   "key": "credit",
   "label": "Credit the author",
   "value": "Not checked yet",
   "status": "unknown",
   "sub": null,
   "quote": null,
   "note": null,
   "source": {
    "label": "huggingface.co",
    "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/README.md"
   },
   "n": 3
  },
  {
   "key": "agent_access",
   "label": "Agent access",
   "value": "Download",
   "status": "info",
   "sub": "Files by hand",
   "quote": null,
   "note": "There is no package or API. Files are downloaded by hand from the official site.",
   "source": {
    "label": "github.com/Tongyi-MAI/Z-Image",
    "url": "https://github.com/Tongyi-MAI/Z-Image"
   },
   "n": 4
  }
 ],
 "license": {
  "name": "Apache-2.0",
  "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/README.md",
  "summary": "License, so paid use is allowed. If you pass the model files on, include the license and keep the notices; the model card sets no separate rules for the pictures you make.",
  "pages_read": 1,
  "rules": [
   "Keep the Apache-2.0 license and notices when you redistribute the weights.",
   "The model card does not add a separate output license; check the repo before shipping."
  ],
  "rows": [
   {
    "label": "Commercial use",
    "value": "Yes",
    "status": "yes",
    "quote": "license: apache-2.0",
    "source": {
     "label": "huggingface.co",
     "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/README.md"
    },
    "note": null
   },
   {
    "label": "Credit",
    "value": "Not stated",
    "status": "unknown",
    "quote": null,
    "source": null,
    "note": null
   },
   {
    "label": "Inside your app or game",
    "value": "Can ship inside your app",
    "status": "yes",
    "quote": "license: apache-2.0",
    "source": {
     "label": "huggingface.co",
     "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/README.md"
    },
    "note": null
   },
   {
    "label": "Pass the files on to your users",
    "value": "With conditions",
    "status": "cond",
    "quote": "You must give any other recipients of the Work or Derivative Works a copy of this License",
    "source": {
     "label": "LICENSE on GitHub",
     "url": "https://github.com/Tongyi-MAI/Z-Image/blob/main/LICENSE"
    },
    "note": "Passing on the weights or code needs a copy of the Apache-2.0 license, change notices and kept attribution notices."
   },
   {
    "label": "AI training",
    "value": "Not stated",
    "status": "unknown",
    "quote": null,
    "source": null,
    "note": null
   },
   {
    "label": "Bots and bulk downloads",
    "value": "Not stated",
    "status": "unknown",
    "quote": null,
    "source": null,
    "note": null
   }
  ],
  "checked_at": "2026-10-27",
  "commercial_use_page": "https://agentgid.com/assets/z-image-turbo/commercial-use/"
 },
 "overview": {
  "heading": "Z-Image-Turbo: fast open model for realistic pictures",
  "body": "Z-Image-Turbo is a free image model from Alibaba's Tongyi team that makes pictures from a text description. It is tuned for realistic photos and can write English and Chinese text inside the picture. It runs on your own computer with a gaming-class graphics card, and the Apache-2.0 license allows paid use."
 },
 "uses": [
  {
   "title": "Realistic photos for a site or app",
   "text": "Make photo-like pictures from a description, such as a cozy cafe interior for a landing page, on your own machine without paying per image.",
   "idea": false,
   "image": null
  },
  {
   "title": "Posters and banners with lettering",
   "text": "Ask for a picture that includes a short headline or sign text in English or Chinese, for example a poster or a shop sign.",
   "idea": false,
   "image": null
  },
  {
   "title": "Images on a gaming graphics card",
   "text": "Run it at home or in the office on a graphics card with 16 GB of memory; with memory saving turned on, smaller cards can work too, only slower.",
   "idea": false,
   "image": null
  },
  {
   "title": "Fast image step in your own service",
   "text": "An app that makes images for its users calls the model on its own server; only 8 model steps per picture keep each request short.",
   "idea": false,
   "image": null
  },
  {
   "title": "Blog and article cover images",
   "text": "Make a matching cover picture for each new post from its title and a short style line, then pick the best of a few seeds.",
   "idea": true,
   "image": null
  },
  {
   "title": "Product mockups for a pitch",
   "text": "Show a product idea in a realistic setting, such as a bottle on a kitchen counter, before any real photo shoot.",
   "idea": true,
   "image": null
  }
 ],
 "start": {
  "prompt": "In a Python venv on our NVIDIA GPU machine, install diffusers with ZImagePipeline, load Tongyi-MAI/Z-Image-Turbo in bfloat16, and write a script that saves a 1024x1024 PNG per prompt with num_inference_steps=9 and guidance_scale=0.0.",
  "install": "pip install git+https://github.com/huggingface/diffusers",
  "install_note": null,
  "code": [
   {
    "tab": "Step 1",
    "intro": "Load the Turbo model in bfloat16 and move it to the graphics card.",
    "source": "pipe = ZImagePipeline.from_pretrained(\n    \"Tongyi-MAI/Z-Image-Turbo\",\n    torch_dtype=torch.bfloat16,\n    low_cpu_mem_usage=False,\n)\npipe.to(\"cuda\")"
   },
   {
    "tab": "Step 2",
    "intro": "Generate with 9 steps and guidance 0, then save the picture.",
    "source": "image.save(\"example.png\")"
   }
  ]
 },
 "mistakes": [
  {
   "dont": "Using guidance_scale 3.5 to 7 and 30 to 50 steps as with other image models",
   "fix": "num_inference_steps=9 and guidance_scale=0.0 for Turbo",
   "why": "The Turbo model is distilled for 8 steps without guidance.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "Loading with StableDiffusionPipeline or an old diffusers release",
   "fix": "Use ZImagePipeline from a diffusers version that includes Z-Image support",
   "why": "Z-Image support was added to diffusers recently, so older releases do not have ZImagePipeline.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "Calling pipe.to(\"cuda\") on a card with less than 16 GB and getting out-of-memory errors",
   "fix": "Call pipe.enable_model_cpu_offload() instead of pipe.to(\"cuda\")",
   "why": "Offloading keeps only the active part of the model on the card.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "Using Turbo as the base for LoRA or style training",
   "fix": "Train on the base Z-Image model, which the makers mark as easy to fine-tune",
   "why": "The model table lists fine-tunability for Turbo as N/A.",
   "dont_code": false,
   "fix_code": false
  }
 ],
 "agent": {
  "self_serve": false,
  "self_serve_text": null,
  "install": null,
  "repo": "https://github.com/Tongyi-MAI/Z-Image",
  "api_docs": null,
  "api_account": "Not needed. Everything runs on your side.",
  "get_files": null,
  "formats": [],
  "limits": null,
  "mcp": null,
  "mcp_url": null,
  "credit_line": null,
  "rules_text": "- Z-Image-Turbo (AI image generators). Efficient open-weights image generation model built on a single-stream diffusion transformer. Price: free; commercial use OK.\n  Connect: download from https://huggingface.co/Tongyi-MAI/Z-Image-Turbo (no API).\n  Rule: Keep the Apache-2.0 license and notices when you redistribute the weights.\n  Rule: The model card does not add a separate output license; check the repo before shipping.\n  License: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/blob/main/README.md (checked 2026-10-27; details: https://agentgid.com/assets/z-image-turbo/)",
  "agent_md": "https://agentgid.com/assets/z-image-turbo/agent.md",
  "card_json": "https://agentgid.com/assets/z-image-turbo/card.json"
 },
 "popularity": {
  "gid_score": 35,
  "stars": 12167,
  "downloads_7d": null,
  "downloads_7d_label": null,
  "downloads_change_4w_pct": null,
  "eco": null,
  "package": null,
  "repo": "Tongyi-MAI/Z-Image",
  "agent_projects": null,
  "agent_projects_total": null,
  "downloads_unconfirmed": false,
  "series": {
   "downloads_weekly": [],
   "stars": [
    [
     "2026-11-07",
     12140
    ],
    [
     "2026-11-08",
     12141
    ],
    [
     "2026-11-09",
     12142
    ],
    [
     "2026-11-10",
     12140
    ],
    [
     "2026-11-11",
     12142
    ],
    [
     "2026-11-12",
     12143
    ],
    [
     "2026-11-13",
     12149
    ],
    [
     "2026-11-14",
     12152
    ],
    [
     "2026-11-15",
     12155
    ],
    [
     "2026-11-16",
     12154
    ],
    [
     "2026-11-17",
     12160
    ],
    [
     "2026-11-18",
     12164
    ],
    [
     "2026-11-19",
     12167
    ]
   ]
  },
  "stars_flat_since": null,
  "updated_at": "2026-11-19"
 },
 "alternatives": [
  {
   "slug": "z-image-turbo",
   "name": "Z-Image-Turbo",
   "why": null,
   "current": true,
   "price": "Free",
   "commercial": {
    "value": "Commercial OK",
    "status": "yes"
   },
   "access": "Download"
  },
  {
   "slug": "sdxl",
   "name": "Stable Diffusion XL base 1.0",
   "why": "Pick Stable Diffusion XL for an older, widely supported open model with a separate refiner and many community add-ons.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "Download"
  },
  {
   "slug": "flux-1-dev",
   "name": "FLUX.1 [dev]",
   "why": "Pick FLUX.1 [dev] only for non-commercial work; commercial use of its weights needs a paid license.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "Non-commercial",
    "status": "no"
   },
   "access": "Download"
  },
  {
   "slug": "openai-gpt-image",
   "name": "OpenAI GPT Image",
   "why": "Pick OpenAI GPT Image when you want a paid hosted service with image editing and no own graphics card.",
   "current": false,
   "price": "Paid",
   "commercial": {
    "value": "Commercial OK",
    "status": "yes"
   },
   "access": "API, npm, PyPI"
  },
  {
   "slug": "invokeai",
   "name": "InvokeAI",
   "why": "Free open-source, self-hosted AI image generation app with a layer-based canvas and node-based workflows.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "Commercial OK",
    "status": "yes"
   },
   "access": "Download"
  },
  {
   "slug": "hunyuandit",
   "name": "HunyuanDiT",
   "why": "Tencent's diffusion-transformer text-to-image model with fine-grained Chinese and English prompt understanding.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "Download"
  }
 ],
 "faq": [
  {
   "q": "Can I use the pictures in a paid product?",
   "a": "The model is under Apache-2.0, which allows commercial use, and the model card adds no separate rules for outputs."
  },
  {
   "q": "Can I try it before installing?",
   "a": "Yes, the makers link an online demo on Hugging Face Spaces and on ModelScope."
  },
  {
   "q": "Why is guidance set to 0?",
   "a": "The Turbo model is distilled to work without guidance; the official example says guidance should be 0 for it."
  },
  {
   "q": "Can it edit an existing picture?",
   "a": "Not this model. Editing is the job of a separate Z-Image-Edit model, which the model table lists as not yet released."
  }
 ],
 "at_a_glance": {
  "latest_version": "diffusers from git main as the README installs it (2026-11-10); weights last changed on Hugging Face 2026-01-30",
  "last_commit": "2026-02-09",
  "runtime": "Python with PyTorch, an NVIDIA GPU with bfloat16 support (16 GB VRAM per the card, less with CPU offload), about 33 GB of disk for the weights",
  "key_needed": false
 },
 "good_to_know": [
  "The download is large, about 33 GB of model files, so plan disk space and the first download time.",
  "The Turbo version trades variety for speed and is not meant for further training. The base Z-Image model is the one for training your own style.",
  "The official examples expect an NVIDIA graphics card; memory saving helps on smaller cards.",
  "Speed and ranking numbers on the pages come from the makers and leaderboards they cite, not from independent tests."
 ],
 "stack_snippets": [],
 "claims": [
  "Matches or exceeds leading competitors with only 8 model steps",
  "Ranked 8th overall on the Artificial Analysis text-to-image leaderboard",
  "Runs with as little as 4GB of graphics memory through the community engine stable-diffusion.cpp"
 ],
 "checked": {
  "license_read": "2026-10-27",
  "overview_checked": "2026-11-10",
  "numbers_updated": "2026-11-19",
  "sources": [
   {
    "label": "huggingface.co/Tongyi-MAI/Z-Image-Turbo",
    "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo/raw/main/README.md"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/api/models/Tongyi-MAI/Z-Image-Turbo"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/api/models/Tongyi-MAI/Z-Image-Turbo/tree/main?recursive=1"
   },
   {
    "label": "README on GitHub",
    "url": "https://github.com/Tongyi-MAI/Z-Image/blob/main/README.md"
   },
   {
    "label": "LICENSE on GitHub",
    "url": "https://github.com/Tongyi-MAI/Z-Image/blob/main/LICENSE"
   },
   {
    "label": "github.com/Tongyi-MAI/Z-Image/commits/main.atom",
    "url": "https://github.com/Tongyi-MAI/Z-Image/commits/main.atom"
   },
   {
    "label": "github.com/Tongyi-MAI/Z-Image",
    "url": "https://github.com/Tongyi-MAI/Z-Image"
   }
  ],
  "unverified": null
 },
 "user_reports": null,
 "url": "https://agentgid.com/assets/z-image-turbo/",
 "note": "Written by AgentGid from the official pages in checked.sources; quotes are copied from those pages. status: yes | cond | no | unknown | info. Prices and vendor claims are as reported on the checked date. Not legal advice."
}
