AI models
UniDiffuser (多模态大模型)
Training compute
2×10²² FLOP
Published
May 30, 2023
UniDiffuser (多模态大模型) is an AI model developed by ShengShu, Tsinghua University and Beijing Academy of Artificial Intelligence / BAAI (China), first published in May 2023. It works in the image generation domain, on tasks such as text-to-image, image captioning, image generation and image-to-image.
Training it took an estimated 2×10²² FLOP of compute (estimation method: hardware). Training ran on 88 NVIDIA A100 SXM4 80 GB for about 672 hours.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- ShengShu, Tsinghua University, Beijing Academy of Artificial Intelligence / BAAI
- Country of organization
- China
- Domain
- Image generation
- Task
- Text-to-image, Image captioning, Image generation, Image-to-image
- Training compute
- 2×10²² FLOP
- Compute estimation method
- Hardware
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 88
- Training time
- 672 h
- Training power draw
- 70.1 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- 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