Hunyuan Video

Training compute

1.5×10²³ FLOP

Parameters

13B

Published

Dec 3, 2024

Hunyuan Video is an AI model developed by Tencent (China), first published in December 2024. It works in the video domain, on tasks such as video generation and text-to-video.

Training it took an estimated 1.5×10²³ FLOP of compute (estimation method: reported,operation counting). The model has 13,000,000,000 parameters.

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

Full record

Organization: Tencent
Country of organization: China
Domain: Video
Task: Video generation, Text-to-video
Training compute: 1.5×10²³ FLOP
Compute estimation method: Reported, Operation counting
Parameters: 13,000,000,000
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Confident