World's First Bilingual Video AI
Breakthrough capability to generate both Chinese and English text directly within video frames with various fonts and effects - the only model supporting dynamic bilingual content.
Versatile video model with strong creative capabilities. Excels at artistic styles, anime, and imaginative content with consistent quality.
Loading video...
Prompt:
In the style of a studio ghibli anime, a boy and his dog run up a grassy scenic mountain with gorgeous clouds, overlooking a village in the distant background.
Breakthrough capability to generate both Chinese and English text directly within video frames with various fonts and effects - the only model supporting dynamic bilingual content.
Revolutionary Mixture-of-Experts design with 27 billion total parameters, 14 billion active during inference. Maximizes capacity while maintaining computational efficiency.
Wan-VAE encodes and decodes unlimited-length 1080p videos without losing temporal information, making it ideal for long-form content and complex video generation tasks.
Covers Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, Video-to-Audio, and FLF2V (First&Last-Frame-to-Video) with multi-GPU acceleration support.
Outstanding performance on authoritative VBench benchmark, excelling in complex dynamics, spatial relationships, and multi-object interactions with SOTA results.
Meticulously curated aesthetic dataset with detailed labels for lighting, composition, contrast, and color tone, enabling precise cinematic style control from noir to commercial-grade.
Wan is the first comprehensive open-source video generation suite under Apache 2.0 license, including full source code, models, and documentation. It's also the world's first AI model capable of generating bilingual (Chinese/English) text within videos.
Still have questions? Contact our support team
Unlock the power of the world's most advanced open-source video generation model. Create bilingual content with professional quality and unlimited creative potential.