Wan 2.2 Image to Video Generator (Lightning) ⚡

Image-to-video AI generator — turn any photo into a smooth, high-quality AI video in 15–60 seconds, powered by Wan 2.2 A14B Lightning, one of the best open image-to-video models available. No GPU, no subscription, no monthly fees: you pay a small fixed price per video. A fast, affordable alternative to Runway, Google Veo, and Kling.

Perfect for TikTok / Reels / YouTube Shorts automation, faceless video channels, product ads, talking-photo (photo-to-video) content, n8n / Make / Zapier workflows, and AI agents.

Demo

Source image	Generated video

Prompt: "The cute girl is dancing with her GLC 300" — 480p, 1:1, 5 seconds, generated in under a minute.

Why this Actor?

• ⚡ Fast — Lightning-distilled Wan 2.2 on dedicated GPUs generates a video in 15–60 seconds on average (most hosted endpoints take minutes).
• 💸 Cheap — a fraction of the price of Veo, Runway, or Kling. Pay only for successful videos; failed runs are never charged.
• 🎬 Quality — Wan 2.2 A14B is a 14-billion-parameter video model with excellent motion coherence and prompt following.
• 🔌 Automation-ready — call it from the Apify API, n8n, Make, Zapier, LangChain, or any AI agent via MCP.
• 📐 Social formats built in — 16:9 (YouTube), 9:16 (TikTok, Reels, Shorts), 1:1 (square), 4:3 and 3:4.
• ⏱️ Flexible length — any duration from 2 to 10 seconds, priced per second.

How it compares

	This Actor (Wan 2.2 Lightning)	Runway / Veo / Kling
Pricing model	Pay per video (per second)	Monthly subscription / credits
Commitment	None — pay only for what you run	Recurring plan, credits expire
Failed runs	Never charged	Often consume credits
Speed	15–60 seconds	Seconds to several minutes
API & automation	Native Apify API, n8n, Make, Zapier, MCP	Varies / limited
Social formats	16:9, 9:16, 1:1, 4:3, 3:4 built in	Varies
Watermark	None	Often on lower tiers

Great when you want image-to-video on demand without a subscription — ideal for occasional use, automated pipelines, and pay-as-you-go scaling.

How it works

1. Provide an image URL (the first frame) and a prompt describing the motion you want.
2. The Actor generates the video and stores it in the run's dataset and key-value store.
3. Download the MP4 from the output, or pipe the URL into the next step of your workflow.

Input example

{
    "imageUrl": "https://example.com/portrait.jpg",
    "prompt": "A beautiful woman is dancing in the park, gentle camera zoom",
    "resolution": "480p",
    "aspectRatio": "9:16",
    "duration": 5,
    "negativePrompt": "blur, distort, and low quality"
}

Output example

{
    "videoUrl": "https://cdn.../video.mp4",
    "apifyVideoUrl": "https://api.apify.com/v2/key-value-stores/.../records/video.mp4",
    "prompt": "A beautiful woman is dancing in the park, gentle camera zoom",
    "resolution": "480p",
    "aspectRatio": "9:16",
    "duration": 5,
    "requestId": "req-..."
}

Pricing

You are charged per second of successful video, based on resolution — a 5-second 480p clip costs just $0.10:

Resolution	Price per second	5s video	10s video
480p	$0.02	$0.10	$0.20
580p	$0.025	$0.125	$0.25
720p	$0.035	$0.175	$0.35

Choose any duration from 2 to 10 seconds. Failed generations are never charged.

Tips for great results

• Describe motion, not appearance — the image already defines how things look. Good: "she turns her head and smiles, wind in her hair, slow zoom in". Weak: "a beautiful woman".
• Add simple camera directions: "slow zoom in", "camera pans left", "static camera".
• Use the negative prompt to suppress artifacts: "blur, distortion, low quality, warped face".
• For seamless loops or transitions, set an end image URL — the video will morph from the start frame to the end frame.

Use it from the API

curl -X POST "https://api.apify.com/v2/acts/danitn11~wan22-lightning-image-to-video/runs?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ "imageUrl": "https://example.com/photo.jpg", "prompt": "slow zoom in, cinematic" }'

Works the same from the Apify n8n node, Make, Zapier, LangChain, or the Apify MCP server for AI agents.

For the full request/response shape (run-sync, async, polling, downloading the MP4), see the OpenAPI spec at ./openapi.yaml — import it into Postman, Insomnia, or any OpenAPI client.

Templates & integrations

Drop this Actor into a no-code workflow to automate video generation end to end. In each tool, search for the Apify connector, authenticate with your Apify API token, and select danitn11/wan22-lightning-image-to-video with the action Run Actor (or Run Actor and get dataset items to receive the video URL back).

• n8n — add the Apify node → Run Actor, map imageUrl and prompt from a previous step (e.g. a new file in Google Drive or an RSS item), then push the resulting videoUrl to your publishing node.
• Make.com — use the Apify › Run an Actor module, then a Watch / Get dataset items module to read back videoUrl. Chain into Buffer, Google Drive, or a social uploader.
• Zapier — trigger (new row, form submission, etc.) → Apify: Run Actor → action (post to TikTok/YouTube, save to Drive, send a Slack message).

Common pattern — automated faceless video pipeline:

New image (Drive / Sheet / webhook)
  → Run this Actor (imageUrl + prompt)
  → Get videoUrl
  → Post to TikTok / Reels / YouTube Shorts (or save to storage)

Use with AI agents (MCP server)

This Actor works as a tool for any MCP-compatible AI agent (Claude, Cursor, VS Code Copilot, custom agents) through Apify's hosted MCP server. Your agent can generate videos as part of a larger task — "make a product video and post it" — with billing through your Apify account.

Server URL (with this Actor preselected as a tool):

https://mcp.apify.com?tools=danitn11/wan22-lightning-image-to-video

Authenticate with OAuth (you'll be redirected on first connect) or an Authorization: Bearer <APIFY_TOKEN> header.

Claude Code

$claude mcp add --transport http apify "https://mcp.apify.com?tools=danitn11/wan22-lightning-image-to-video" -H "Authorization: Bearer <APIFY_TOKEN>"

Claude Desktop / claude.ai — add a custom connector with the server URL above (OAuth flow handles auth).

Cursor / VS Code — add to .cursor/mcp.json (or "MCP: Open User Configuration" in VS Code):

{
    "mcpServers": {
        "apify": {
            "url": "https://mcp.apify.com?tools=danitn11/wan22-lightning-image-to-video",
            "headers": { "Authorization": "Bearer <APIFY_TOKEN>" }
        }
    }
}

Local stdio (npx)

{
    "mcpServers": {
        "apify": {
            "command": "npx",
            "args": ["-y", "@apify/actors-mcp-server", "--tools", "danitn11/wan22-lightning-image-to-video"],
            "env": { "APIFY_TOKEN": "<APIFY_TOKEN>" }
        }
    }
}

Then just ask your agent: "Generate a 5-second 9:16 video from https://example.com/photo.jpg — slow zoom in, cinematic." The agent calls the Actor, waits for the result, and gets back the video URL from the output schema.

FAQ

How long does it take to generate a video from an image? Typically 15–60 seconds per video on our dedicated GPUs.

What image formats are supported? JPG, PNG, and WebP via a publicly accessible URL.

Is there a watermark? No. The output MP4 is clean and ready to publish.

What model is used? Wan 2.2 A14B (image-to-video) with Lightning distillation for fast inference.