Wan-AI/Wan2.1-T2V-1.3B-Diffusers is a text-to-video diffusion model. It excels in generating 480P videos from text prompts efficiently on consumer-grade GPUs, requiring only 8.19GB of VRAM, while maintaining competitive video quality.

Some other noteworthy features of Wan-AI/Wan2.1-T2V-1.3B-Diffusers include multilingual support (English and Chinese), image-to-video conversion, aspect ratio control, visual text rendering inside videos, prompt enhancement, and the ability to add sound effects or background music to generated videos.

Metric	Value
Parameter Count	1.3 billion
Mixture of Experts	No
Context Length	Unknown
Multilingual	Yes
Quantized*	No

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