Wan 2.1 14B I2V

Training compute

2.5×10²³ FLOP

Parameters

14B

Published

Feb 25, 2025

Wan 2.1 14B I2V is an AI model developed by Alibaba (China), first published in February 2025. It works in the video and vision domain, on tasks such as video generation, image-to-video and text-to-video.

Training it took an estimated 2.5×10²³ FLOP of compute (estimation method: operation counting). The model has 14,000,000,000 parameters. It was trained on roughly 3T datapoints.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Alibaba
Country of organization: China
Domain: Video, Vision
Task: Video generation, Image-to-video, Text-to-video
Training compute: 2.5×10²³ FLOP
Compute estimation method: Operation counting
Parameters: 14,000,000,000
Dataset size: 3T
Numerical format: BF16
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Likely