Open source video is back

Posted July 31, 2025 by
$0.05 per video, ~30s per generation

Try WAN 2.2

Wan 2.2 has set the open source video community ablaze.

It’s a huge leap forward from 2.1 with sharp physics, faster generation, and more control. And because it’s fully open source, it opens the door to high-quality video tools for anyone at an astounding fraction of the cost.

We’ve teamed up with Pruna AI to release our own optimized version of Wan 2.2. You can test it in these ways:

You heard right. 5 cents a video. That’s even less than leading image generators on the AI market.

With inference times at ~30s, Wan 2.2 can become your leading way to rapidly test video prompts.

And don’t let the fast inference time fool you — these Wan 2.2 optimizations do not comprise on quality.

We are also offering Wan 2.2 i2v at 480p and 720p without optimizations:

Wan 2.2 API

Running WAN 2.2 is straightforward with Replicate’s API. Here’s how to generate your first video using the text-to-video model:

import Replicate from "replicate";

const replicate = new Replicate();
const model = "wan-video/wan-2.2-t2v-fast";
const input = {
  prompt: "A serene mountain lake at sunset with gentle ripples on the water",
};

const output = await replicate.run(model, { input });
console.log(output);

For image-to-video generation, simply add an image input with the i2v fast endpoint:

import Replicate from "replicate";

const replicate = new Replicate();
const model = "wan-video/wan-2.2-i2v-fast";
const input = {
  image: "https://example.com/your-image.jpg",
  prompt: "The leaves rustle gently in the wind",
};

const output = await replicate.run(model, { input });
console.log(output);

We plan to release more optimizations with Pruna over the next couple of days. Make sure you follow Replicate to keep up with the latest in our Wan 2.2 journey.

Join us

Check out all the Wan 2.2 models

Try WAN 2.2