Wan-AI/Wan2.2-T2V-A14B-Diffusers is a large vision model (LVM) designed for text-to-video generation using a Mixture-of-Experts (MoE) diffusion architecture.

It excels in generating high-quality, professional-grade 480p and 720p videos from text prompts, leveraging 14 billion active parameters per inference step for detailed and coherent video synthesis while maintaining efficient GPU memory usage.

Some other noteworthy features of Wan-AI/Wan2.2-T2V-A14B-Diffusers include support for image-to-video generation and the ability to handle advanced creative storytelling, marketing content, and filmmaking pre-visualization tasks.

Metric	Value
Parameter Count	27 billion (14B active)
Mixture of Experts	Yes
Active Parameter Count	14 billion
Context Length	Unknown
Multilingual	Unknown
Quantized*	No

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