Wan-AI/Wan2.2-TI2V-5B-Diffusers is a Large Vision Model (LVM) designed for efficient text-to-video and image-to-video generation using a unified diffusion-based framework. It excels in enabling rapid, high-quality 720P@24fps video synthesis from either text or images, with a 5-billion parameter architecture optimized for consumer-grade hardware and fast inference.

Some other noteworthy features of Wan-AI/Wan2.2-TI2V-5B-Diffusers include advanced compression via the Wan2.2-VAE for efficient video reconstruction, and support for practical deployment scenarios such as rapid prototyping, educational use, and workflows where hardware resources are limited.

Metric	Value
Parameter Count	5 billion
Mixture of Experts	No
Context Length	Unknown
Multilingual	No
Quantized*	No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.