Wan: An Open and Advanced Large-scale Video Generation Model

In this repository, we present Wan2.1, a comprehensive and open foundational video model that pushes the boundaries of video generation. Wan2.1 offers the following key features:

• 👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions in multiple benchmark tests.
• 👍Support for Consumer-grade GPUs: The T2V 1.3B model requires only 8.19 GB of VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models.
• 👍Multi-task Capability: Wan2.1 excels in text-to-video, image-to-video, video editing, text-to-image, and video-to-audio tasks, advancing the field of video generation.
• 👍Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring powerful text generation capabilities that enhance its practical applications.
• 👍Powerful Video VAE: Wan VAE provides exceptional efficiency and performance, enabling encoding and decoding of 1080P videos of arbitrary length while preserving temporal information, making it an ideal foundation for video and image generation.