AI models
MindEye2
Published
Jun 15, 2024
MindEye2 is an AI model developed by Stability AI, Medical AI Research Center (MedARC), Princeton University, University of Minnesota, University of Sydney and University of Waterloo (United Kingdom, United States, Australia and Canada), first published in June 2024. It works in the medicine, vision and image generation domain, on tasks such as image captioning and image generation.
Epoch AI has no training-compute estimate for this model. Training ran on 8 NVIDIA A100 SXM4 80 GB.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Stable Diffusion XL (SDXL). Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- Stability AI, Medical AI Research Center (MedARC), Princeton University, University of Minnesota, University of Sydney, University of Waterloo
- Country of organization
- United Kingdom, United States, Australia, Canada
- Domain
- Medicine, Vision, Image generation
- Task
- Image captioning, Image generation
- Compute estimation method
- Hardware
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 8
- Chip-hours
- 24
- Training power draw
- 6.3 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- Stable Diffusion XL (SDXL)
- Epoch confidence
- Likely
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