AI models
Pyramid Flow
Training compute
7.7×10²¹ FLOP
Parameters
2B
Published
Oct 8, 2024
Pyramid Flow is an AI model developed by Peking University, Kuaishou Technology and Beijing University of Posts and Telecommunications (China), first published in October 2024. It works in the video domain, on tasks such as video generation and text-to-video.
Training it took an estimated 7.7×10²¹ FLOP of compute. The model has 2,000,000,000 parameters. Training ran on 128 NVIDIA A100 for about 162 hours.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 294 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Peking University, Kuaishou Technology, Beijing University of Posts and Telecommunications
- Country of organization
- China
- Domain
- Video
- Task
- Video generation, Text-to-video
- Training compute
- 7.7×10²¹ FLOP
- Parameters
- 2,000,000,000
- Training hardware
- NVIDIA A100
- Chips used
- 128
- Training time
- 162 h
- Chip-hours
- 20.7K
- Training power draw
- 100.8 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 294
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models