Wan2.1-VACE (1.3B, 14B)

Alibaba (Qwen) · 14 May 2025

All-in-one open model for video creation and editing, built on Wan2.1 from the VACE paper, in 1.3B and 14B sizes.

Packages many video generation and editing tasks into a single model rather than one model per task. Apache 2.0; inference code and weights were released together with the paper's technical report.

Date

Wednesday, 14 May 2025

Lab

Alibaba (Qwen)

Kind

open-weights

Access

open weights

Figures

README dates the weights and inference code 2025-05-14 (Hugging Face repos created 2025-05-13).

Sources

1. github.com/Wan-Video/Wan2.1
2. arxiv.org/abs/2503.07598
3. huggingface.co/Wan-AI/Wan2.1-VACE-14B

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

Related

• Wan2.1 (T2V 1.3B and 14B, I2V 14B)