AI models
MultiBand Diffusion
Training compute
2.6×10¹⁹ FLOP
Published
Nov 8, 2023
MultiBand Diffusion is an AI model developed by Meta AI, Hebrew University of Jerusalem and LORIA (United States, Israel and France), first published in November 2023. It works in the audio and speech domain, on tasks such as audio generation.
Training it took an estimated 2.6×10¹⁹ FLOP of compute (estimation method: hardware). Training ran on NVIDIA V100 for about 48 hours. The compute alone is estimated at $23 in 2023 dollars.
Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 43 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Meta AI, Hebrew University of Jerusalem, LORIA
- Country of organization
- United States, Israel, France
- Domain
- Audio, Speech
- Task
- Audio generation
- Training compute
- 2.6×10¹⁹ FLOP
- Compute estimation method
- Hardware
- Training hardware
- NVIDIA V100
- Training time
- 48 h
- Training cost (2023 USD)
- $23
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Citations
- 43
- 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