Seaweed-7B

Training compute

9×10²³ FLOP

Parameters

7B

Published

Apr 11, 2025

Seaweed-7B is an AI model developed by ByteDance (China), first published in April 2025. It works in the video domain, on tasks such as video generation, text-to-video, image-to-video and audio generation.

Training it took an estimated 9×10²³ FLOP of compute (estimation method: hardware). The model has 7,000,000,000 parameters. Training ran on NVIDIA H100 SXM5 80GB.

Access: Unreleased. Its weights are not openly released. The reference paper has 83 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: ByteDance
Country of organization: China
Domain: Video
Task: Video generation, Text-to-video, Image-to-video, Audio generation
Training compute: 9×10²³ FLOP
Compute estimation method: Hardware
Parameters: 7,000,000,000
Training hardware: NVIDIA H100 SXM5 80GB
Chip-hours: 665K
Model accessibility: Unreleased
Open weights: No
Citations: 83
Epoch confidence: Confident