Movie Gen Video

Training compute

1.6×10²⁴ FLOP

Parameters

30B

Published

Oct 4, 2024

Movie Gen Video is an AI model developed by Meta AI (United States), first published in October 2024. It works in the video and vision domain, on tasks such as video generation, text-to-video and image-to-video.

Training it took an estimated 1.6×10²⁴ FLOP of compute (estimation method: operation counting). The model has 30,000,000,000 parameters. It was trained on roughly 3.4B datapoints. Training ran on 6,144 NVIDIA H100 SXM5 80GB for about 331 hours.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Video, Vision
Task: Video generation, Text-to-video, Image-to-video
Training compute: 1.6×10²⁴ FLOP
Compute estimation method: Operation counting
Parameters: 30,000,000,000
Dataset size: 3.4B
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 6,144
Training time: 331 h
Training power draw: 8.5 MW
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident