Wan: Open and Advanced Large-Scale Video Generative Models
Create 3D models and videos from images
Generate video from text description
Create simple videos from image sequences
Wan: Open and Advanced Large-Scale Video Generative Models
Huggingface demo of TrajectoryCrafter
Wan: Open and Advanced Large-Scale Video Generative Models
Generate a 4-second video from an image
Text-to-Video
Generate a video from text and images
Generate 3D videos from images
Generate videos from text or images
Generate a video from a prompt and an image
Wan2.1 is an advanced large-scale video generative model designed to create high-quality videos from text or image inputs. It leverages cutting-edge AI technology to transform static images or text descriptions into dynamic video content, enabling users to bring their creative visions to life.
• Video Generation from Text/Images: Create videos from text prompts or image inputs with high precision and detail. • High-Quality Output: Produce videos with exceptional clarity and realism. • Customization Options: Fine-tune video settings, such as duration, resolution, and style, to match your preferences. • Advanced AI Technology: Built on state-of-the-art models to ensure superior performance and accuracy. • User-Friendly Interface: Easy-to-use platform for seamless video creation.
What file formats does Wan2.1 support for input?
Wan2.1 supports standard image formats like JPEG, PNG, and BMP for image inputs. For text inputs, simply enter your description in the provided text box.
Can I customize the video after generation?
Yes, Wan2.1 allows you to adjust video settings such as resolution, duration, and style before generation. However, post-generation editing may require external tools.
How long does video generation typically take?
Generation time varies depending on the complexity of the input and selected settings. Typically, it ranges from a few seconds to several minutes for high-resolution videos.