Alibaba's open-source AI video platform for text-to-video, image-to-video, and editing
Wan AI is Alibaba's open-source AI creative platform built around the Wan 2.x video generation model series, designed to lower the barrier to AI video creation for developers and creators worldwide. The Wan model is notable for being the first video model capable of generating bilingual text in both Chinese and English within video frames — a significant advantage for international content. Wan AI supports a broad range of creation modes from a unified interface: text-to-video, image-to-video, text-to-image, image-to-image transformation, image editing, style transfer, and super resolution. The lightweight 1.3B parameter variant of Wan requires only 8.19 GB VRAM and generates a 5-second 480P video on an RTX 4090 in approximately 4 minutes, making it one of the most hardware-accessible open-source video models. The high-performance 14B parameter model produces higher-quality output suitable for professional production. Wan AI is accessible via its official web platform at wan.video, the Hugging Face demo space, and through community API providers. As an Alibaba open-source release, the model weights and training framework are freely available on GitHub and Hugging Face for developers wishing to self-host, fine-tune, or integrate Wan into custom pipelines.
Explore other tools in this category
All top AI video models in one platform — generate from text, image, or video
Generate 1080p cinematic videos up to 15 seconds from text or images
Google DeepMind's cinematic video model with native synchronized audio
ByteDance's dual-branch AI video model with natively synchronized cinematic audio
Create cinematic AI videos from text and images in a unified browser-based workflow
xAI's free AI video generator — turn images into short videos with Grok