alibaba/wan-2-1 models

each::sense is in private beta.
Eachlabs | AI Workflows for app builders

alibaba/wan-2-1

Alibaba's efficient Wan 2.1 model. Balances performance and quality for scalable tasks.

Models

Wan 2.1 14B is an image-to-video model, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Wan 2.1 | Image to Video | 480P

Accelerated inference for Wan 2.1 I2v 720P image to video with high resolution, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.

Wan 2.1 | Image to Video | 720P

Wan is an advanced and powerful video generation model developed by Tongyi Lab of Alibaba Group to generate 5-second, 480p videos.

Wan 2.1 | 1.3B
FREQUENTLY ASKED QUESTIONS

Dev questions, real answers.

An earlier, lighter version, often faster but with slightly less detail than v2.6.

Yes, it is optimized for generating content for mobile screens (720p).

Use it on Eachlabs with the pay-as-you-go model.