Wan: Open and Advanced Large-Scale Video Generative Models
Identity-Preserving Text-to-Video Generation
Create a video from a script using AI
Video gen using SkyReels model from HunyuanVideo.
Generate a 4-second video from an image
Apply the motion of a video on a portrait
Wan: Open and Advanced Large-Scale Video Generative Models
First use
Wan: Open and Advanced Large-Scale Video Generative Models
All images and animated first working
Generate a 5-second video from an image
Generate video from image
Generate a video from text
Wan2.1 is an advanced open-source technology designed to generate high-quality videos from images or text prompts. It is part of the Wan series, known for its large-scale video generative models, enabling users to create dynamic video content from static inputs.
• Video Generation: Create videos from images or text descriptions with high fidelity.
• Customizable Output: Adjust video resolution, duration, and frame rate to suit your needs.
• User-Friendly Interface: Intuitive tools for previewing and refining video outputs.
• Multi-Format Support: Export videos in popular formats like MP4, MOV, and more.
• Open-Source Flexibility: Modify and extend the model to fit specific use cases.
What formats does Wan2.1 support for input?
Wan2.1 supports JPEG, PNG, and BMP for image inputs, and plain text for descriptions.
Can I customize the video resolution?
Yes, you can set the resolution to 720p, 1080p, or 4K depending on your requirements.
Is Wan2.1 available for free?
Wan2.1 is open-source and free to use, making it accessible for both personal and commercial projects.