WAN 2.7 is a KIE-hosted Alibaba video model supporting text-to-video, image-to-video, reference-to-video, and video editing workflows.

What inputs does WAN 2.7 support?

Depending on workflow, it supports text prompts, negative prompts, audio URL, first-frame image, reference images, reference videos, reference voice, and source video URL.

How many reference assets can I use?

The reference-to-video workflow supports up to five total reference images and videos, with at most one first-frame image.

What durations are available?

Text-to-video supports 2-15 seconds. Reference workflows commonly support 2-10 seconds. The UI exposes a flexible 2-15 second duration range.

What resolutions and ratios are supported?

WAN 2.7 supports 720p and 1080p output with 16:9, 9:16, 1:1, 4:3, and 3:4 aspect ratios.

How are credits calculated?

Credits are calculated per output second: 16 credits/s for 720p and 24 credits/s for 1080p.

WAN 2.7 - Multimodal AI Video Generation with Text, Image, Video, and Audio References

VORAvideo