AI Research Atlas

Wan2.7 (T2V, I2V, R2V, video edit)

Alibaba (Qwen) · 3 April 2026

Wan2.7 video suite on Alibaba Cloud covers text-, image- and reference-to-video plus instruction-based video editing; 15-second clips.

Alibaba Cloud's docs list first-frame, first-and-last-frame and continuation modes for image-to-video, plus a dedicated video-edit model; 2026-06-12 snapshots refreshed text- and reference-to-video. Marketing also cites a 'thinking mode' and nine reference images. Hosted only.

Date
Friday, 3 April 2026
Lab
Alibaba (Qwen)
Kind
model
Access
closed API

Dates from Alibaba Cloud's Model Studio release list. The press release carrying 'thinking mode' and reference-count claims is a republished wire item of uncertain provenance and discloses no parameter count; third-party blogs cite 27B MoE but this was not confirmed.

Sources

  1. www.alibabacloud.com/help/en/model-studio/newly-released-models
  2. www.marketscreener.com/news/alibaba-launches-wan-2-7-breakthrough-ai-image-video-generatio

This record was checked against its sources on 6 October 2026. How we check

Related