{
 "slug": "wan",
 "name": "Wan 2.2",
 "author": "Wan team (Alibaba)",
 "density": "full",
 "status": "active",
 "status_note": null,
 "alternatives_page": null,
 "one_liner": "Open MoE video model family for text-to-video, image-to-video, speech-to-video and character animation at 480p/720p.",
 "category": {
  "slug": "ai-video",
  "name": "AI video generators and platforms"
 },
 "tags": [
  "Open source"
 ],
 "styles": [],
 "logo_url": "https://agentgid.com/media/avatars/wan-video.png",
 "logo_letter": "W",
 "links": {
  "repo": "https://github.com/Wan-Video/Wan2.2",
  "website": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
  "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 (the 5B model runs on a single RTX 4090).",
   "source": {
    "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
   },
   "n": 1
  },
  {
   "key": "commercial",
   "label": "Commercial use",
   "value": "Yes",
   "status": "yes",
   "sub": "Apache-2.0",
   "quote": "The models in this repository are licensed under the Apache 2.0 License.",
   "note": "Apache 2.0 allows commercial use; generated content must stay within the listed limits.",
   "source": {
    "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
   },
   "n": 2
  },
  {
   "key": "credit",
   "label": "Credit the author",
   "value": "Not needed",
   "status": "yes",
   "sub": "Keep the notice in code copies",
   "quote": "We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license.",
   "note": "No credit on screen. Keep the license notice inside the code you ship.",
   "source": {
    "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
   },
   "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/Wan-Video/Wan2.2",
    "url": "https://github.com/Wan-Video/Wan2.2"
   },
   "n": 4
  }
 ],
 "license": {
  "name": "Apache-2.0",
  "url": "https://github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt",
  "summary": "The Wan 2.2 models are under the Apache 2.0 license, and the makers claim no rights over the videos you make. You may use them in paid work, but you are responsible for the content and must not make harmful or misleading videos.",
  "pages_read": 2,
  "rules": [
   "Keep the Apache-2.0 license and notices when you redistribute the weights.",
   "The model card bars sharing illegal or harmful content, misinformation and personal data meant to harm.",
   "You are fully accountable for what you generate."
  ],
  "rows": [
   {
    "label": "Commercial use",
    "value": "Yes",
    "status": "yes",
    "quote": "The models in this repository are licensed under the Apache 2.0 License.",
    "source": {
     "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
     "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
    },
    "note": null
   },
   {
    "label": "Credit",
    "value": "Not needed",
    "status": "yes",
    "quote": "We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license.",
    "source": {
     "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
     "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
    },
    "note": null
   },
   {
    "label": "Inside your app or game",
    "value": "Can ship inside your app",
    "status": "yes",
    "quote": "The models in this repository are licensed under the Apache 2.0 License.",
    "source": {
     "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
     "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
    },
    "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": "github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt",
     "url": "https://github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt"
    },
    "note": "Passing on the weights or code needs a copy of the license and the notices."
   },
   {
    "label": "Monetized YouTube",
    "value": "Allowed",
    "status": "yes",
    "quote": "We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license.",
    "source": {
     "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
     "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
    },
    "note": null
   },
   {
    "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": "2026-10-25",
  "commercial_use_page": "https://agentgid.com/assets/wan/commercial-use/"
 },
 "overview": {
  "heading": "Wan 2.2: open AI models that make short videos",
  "body": "Wan 2.2 is a free, open family of AI video models from Alibaba's Wan team. It makes short video clips from a written description and brings a still picture to life. It can also make a person in a photo talk or dance along with sound or another video. You run it on your own powerful graphics card, and you may use the clips in paid work."
 },
 "uses": [
  {
   "title": "A clip from a written idea",
   "text": "Describe a scene in a sentence, such as two cats boxing on a stage, and get a short 720p video. Useful for social posts, mood videos or story drafts.",
   "idea": false,
   "image": null
  },
  {
   "title": "Bring a product photo to life",
   "text": "Start from your own picture, such as a product shot or an illustration, and add movement described in words. The video keeps the shape of the picture.",
   "idea": false,
   "image": null
  },
  {
   "title": "A talking or singing person from audio",
   "text": "Give one photo of a person and a voice or song recording. The model makes a video of that person speaking or singing along, as long as the audio.",
   "idea": false,
   "image": null
  },
  {
   "title": "Make a character copy a dance",
   "text": "Take a video of someone moving and a picture of a character. The character repeats the moves, or replaces the person in the video.",
   "idea": false,
   "image": null
  },
  {
   "title": "Make videos from Python code",
   "text": "Call the model from a Python script, for example to make a batch of clips for a product catalog.",
   "idea": false,
   "image": null
  },
  {
   "title": "Moving backgrounds for a landing page",
   "text": "Make a calm looping clip, like waves or clouds, from a short description and use it as the hero video of a site.",
   "idea": true,
   "image": null
  }
 ],
 "start": {
  "prompt": "On my machine with a 24 GB NVIDIA card, set up Wan2.2 from github.com/Wan-Video/Wan2.2, download Wan-AI/Wan2.2-TI2V-5B, and make a 1280*704 clip from my prompt with --offload_model True --convert_model_dtype --t5_cpu; do not use DashScope prompt extension.",
  "install": null,
  "install_note": null,
  "code": [
   {
    "tab": "Step 1",
    "intro": "Get the code and install the packages. PyTorch 2.4 or newer is needed; install flash_attn last if it fails.",
    "source": "git clone https://github.com/Wan-Video/Wan2.2.git\ncd Wan2.2\n# Ensure torch >= 2.4.0\npip install -r requirements.txt"
   },
   {
    "tab": "Step 2",
    "intro": "Download a model. The 5B model is the one that fits a single 24 GB card.",
    "source": "huggingface-cli download Wan-AI/Wan2.2-TI2V-5B --local-dir ./Wan2.2-TI2V-5B"
   },
   {
    "tab": "Step 3",
    "intro": "Run generate.py with the task, size, model folder and your prompt.",
    "source": "python generate.py --task ti2v-5B --size 1280*704 --ckpt_dir ./Wan2.2-TI2V-5B --offload_model True --convert_model_dtype --t5_cpu --prompt \"Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage\""
   }
  ]
 },
 "mistakes": [
  {
   "dont": "--size 1280*720 with --task ti2v-5B",
   "fix": "--size 1280*704 (or 704*1280) for the 5B model",
   "why": "The 5B model uses its own 720P sizes.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "running the A14B or S2V-14B single-GPU commands on a 24 GB card",
   "fix": "use the TI2V-5B model on 24 GB cards; the 14B commands need at least 80 GB or several GPUs",
   "why": "The README states the memory each command needs.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "stopping at an out-of-memory error",
   "fix": "add --offload_model True, --convert_model_dtype and --t5_cpu",
   "why": "These options lower the graphics memory needed.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "--use_prompt_extend --prompt_extend_method 'dashscope' without asking",
   "fix": "use --prompt_extend_method 'local_qwen', or ask the person for a DASH_API_KEY first",
   "why": "The DashScope method sends the prompt to Alibaba Cloud and needs a key the person must create.",
   "dont_code": false,
   "fix_code": false
  },
  {
   "dont": "pip install -r requirements.txt fails on flash_attn and the setup is abandoned",
   "fix": "install the other packages first and flash_attn last",
   "why": "The README gives this order as the fix.",
   "dont_code": true,
   "fix_code": false
  }
 ],
 "agent": {
  "self_serve": false,
  "self_serve_text": null,
  "install": null,
  "repo": "https://github.com/Wan-Video/Wan2.2",
  "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": "Video made with Wan 2.2 (Alibaba Wan team), Apache License 2.0",
  "rules_text": "- Wan 2.2 (AI video generators and platforms). Open MoE video model family for text-to-video, image-to-video, speech-to-video and character animation at 480p/720p. Price: free; commercial use OK; no credit needed.\n  Connect: download from https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B (no API).\n  Rule: Keep the Apache-2.0 license and notices when you redistribute the weights.\n  Rule: The model card bars sharing illegal or harmful content, misinformation and personal data meant to harm.\n  Rule: You are fully accountable for what you generate.\n  License: https://github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt (checked 2026-10-25; details: https://agentgid.com/assets/wan/)",
  "agent_md": "https://agentgid.com/assets/wan/agent.md",
  "card_json": "https://agentgid.com/assets/wan/card.json"
 },
 "popularity": {
  "gid_score": 40,
  "stars": 18766,
  "downloads_7d": null,
  "downloads_7d_label": null,
  "downloads_change_4w_pct": null,
  "eco": null,
  "package": null,
  "repo": "Wan-Video/Wan2.2",
  "agent_projects": null,
  "agent_projects_total": null,
  "downloads_unconfirmed": false,
  "series": {
   "downloads_weekly": [],
   "stars": [
    [
     "2026-11-07",
     18452
    ],
    [
     "2026-11-08",
     18462
    ],
    [
     "2026-11-09",
     18478
    ],
    [
     "2026-11-10",
     18505
    ],
    [
     "2026-11-11",
     18530
    ],
    [
     "2026-11-12",
     18563
    ],
    [
     "2026-11-13",
     18611
    ],
    [
     "2026-11-14",
     18639
    ],
    [
     "2026-11-15",
     18657
    ],
    [
     "2026-11-16",
     18685
    ],
    [
     "2026-11-17",
     18718
    ],
    [
     "2026-11-18",
     18745
    ],
    [
     "2026-11-19",
     18766
    ]
   ]
  },
  "stars_flat_since": null,
  "updated_at": "2026-11-19"
 },
 "alternatives": [
  {
   "slug": "wan",
   "name": "Wan 2.2",
   "why": null,
   "current": true,
   "price": "Free",
   "commercial": {
    "value": "Commercial OK",
    "status": "yes"
   },
   "access": "Download"
  },
  {
   "slug": "ltx",
   "name": "LTX-2 (LTX-2.5)",
   "why": "Pick LTX when you want video with sound made in one step from text, images or audio.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "Download"
  },
  {
   "slug": "stable-video-diffusion",
   "name": "Stable Video Diffusion (SVD-XT)",
   "why": "Pick Stable Video Diffusion for a short clip of 25 frames from one still image.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "Download"
  },
  {
   "slug": "cogvideo",
   "name": "CogVideo / CogVideoX",
   "why": "Pick CogVideoX when you also want ready fine-tuning code for text and image to video.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "Download"
  },
  {
   "slug": "hypit",
   "name": "Hypit",
   "why": "Open-source video toolkit for AI agents that clones reference videos into variants, plus a hosted multi-model video API.",
   "current": false,
   "price": "Free tier",
   "commercial": {
    "value": "With conditions",
    "status": "cond"
   },
   "access": "API, npm"
  },
  {
   "slug": "huobao-drama",
   "name": "Huobao Drama",
   "why": "Open-source platform that automates AI short-drama production from script and characters to storyboard and video compositing.",
   "current": false,
   "price": "Free",
   "commercial": {
    "value": "Non-commercial",
    "status": "no"
   },
   "access": "Download"
  }
 ],
 "faq": [
  {
   "q": "Can I use Wan videos in ads or on YouTube?",
   "a": "Yes. The makers claim no rights over generated videos, and the models are under Apache 2.0; the content must stay lawful and not harmful."
  },
  {
   "q": "Which model runs on one home graphics card?",
   "a": "The TI2V-5B model, on a card with 24 GB of memory such as an RTX 4090."
  },
  {
   "q": "Can it make a video without a written prompt?",
   "a": "Yes, from the image alone; a prompt can be written for you from the picture with the optional prompt rewriting step."
  },
  {
   "q": "Can I set the video shape when I start from an image?",
   "a": "The size you give sets the area; the shape follows your input image."
  }
 ],
 "at_a_glance": {
  "latest_version": "main@1ea34ff",
  "last_commit": "2026-09-21",
  "runtime": "Python with torch>=2.4.0, transformers>=4.49.0,<=4.51.3, diffusers>=0.31.0, flash_attn; NVIDIA GPU with 24 GB (TI2V-5B) or 80 GB (A14B, S2V-14B) of VRAM",
  "key_needed": false
 },
 "good_to_know": [
  "The 5B model needs a graphics card with at least 24 GB of memory, like an RTX 4090. The larger 14B models need 80 GB cards.",
  "The files are big. The 5B model folder alone holds about 34 GB, with single files near 10 GB.",
  "An optional step that rewrites your prompt in more detail can call Alibaba Cloud with a paid key. A local Qwen model can do the same on your machine.",
  "Free online demos exist on Hugging Face and on the wan.video site if you want to try before setting it up.",
  "It also works inside ComfyUI, a visual tool where you connect blocks instead of typing commands."
 ],
 "stack_snippets": [],
 "claims": [
  "Compared with Wan2.1, Wan2.2 is trained on +65.6% more images and +83.2% more videos.",
  "The 5B model makes 720P video at 24fps."
 ],
 "checked": {
  "license_read": "2026-10-25",
  "overview_checked": "2026-11-10",
  "numbers_updated": "2026-11-19",
  "sources": [
   {
    "label": "github.com/Wan-Video/Wan2.2",
    "url": "https://github.com/Wan-Video/Wan2.2"
   },
   {
    "label": "README on GitHub",
    "url": "https://github.com/Wan-Video/Wan2.2/blob/main/README.md"
   },
   {
    "label": "github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt",
    "url": "https://github.com/Wan-Video/Wan2.2/blob/main/LICENSE.txt"
   },
   {
    "label": "github.com/Wan-Video/Wan2.2/blob/main/requirements.txt",
    "url": "https://github.com/Wan-Video/Wan2.2/blob/main/requirements.txt"
   },
   {
    "label": "huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B/raw/main/README.md"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B/raw/main/README.md"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers/raw/main/README.md"
   },
   {
    "label": "huggingface.co",
    "url": "https://huggingface.co/api/models/Wan-AI/Wan2.2-TI2V-5B/tree/main"
   },
   {
    "label": "huggingface.co/Wan-AI/Wan2.2-I2V-A14B",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B"
   },
   {
    "label": "huggingface.co/Wan-AI/Wan2.2-TI2V-5B",
    "url": "https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B"
   }
  ],
  "unverified": null
 },
 "user_reports": null,
 "url": "https://agentgid.com/assets/wan/",
 "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."
}
