Wan API

Wan API's overview

Wan API is a video generation platform designed for developers and creators. It provides a range of tools and models to generate videos from text, images, and multimodal references.

What You Can Do With Wan API

• **Text-to-Video** — Turn text prompts into videos with generated sound, allowing for easy creation of video content from written descriptions or scripts.
• **Image-to-Video** — Create videos from images, enabling the animation of still pictures or the addition of motion to static graphics.
• **Multimodal References** — Use a combination of text, images, and audio references to guide the video generation process, providing more control over the output.
• **Resolution Options** — Choose from various resolution options, including up to 1080p for Wan 3.0 and Prime, and up to 4K for Pro and Prime Pro models.
• **Generated Audio** — Automatically generate audio for videos, eliminating the need for separate audio editing or recording.
• **Customizable Output** — Select the duration, frame shape, and sound for the generated video, allowing for tailored output to fit specific needs or projects.

Wan API's Key Features

🔥 Text to Video Conversion

⚡️ Image to Video

✨ Multimodal References

🚀 Generated Sound

Wan API's FAQ

What is the Wan 3.0 API used for?

The Wan 3.0 API is used to generate videos from text, images, and multimodal references with generated sound.

Which Wan model should I choose for 1080p output?

You can choose Wan 3.0 or Wan 3.0 Prime for output up to 1080p.

How is video priced in the Wan API?

Current rates are shown on each model page and cost depends on resolution and the combined duration of reference video and generated output.

Can I start with an image in the Wan 3.0 API?

Yes, the Wan 3.0 API supports text to video, first/last frame image inputs, and a separate multimodal reference workflow.

Find out more about Wan API

• Twitter