MindEye2
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Stability AI,Medical AI Research Center (MedARC),Princeton University,University of Minnesota,University of Sydney,University of Waterloo
- Organisation type
- Industry,Research collective,Academia,Academia,Academia,Academia
- Country
- United Kingdom of Great Britain and Northern Ireland, United States of America, Australia, Canada
- Published
- 15 June 2024
- Authors
- Paul S. Scotti, Mihir Tripathy, Cesar Kadir Torrico Villanueva, Reese Kneeland, Tong Chen, Ashutosh Narang, Charan Santhirasegaran, Jonathan Xu, Thomas Naselaris, Kenneth A. Norman, Tanishq Mathew Abraham
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Medicine, Vision, Image generation
- Task
- Image captioning, Image generation
- Base model
- Stable Diffusion XL (SDXL)
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- tokens
- Epochs
- 150
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- How it was established
- Hardware
- Fine-tuning compute
- 8.1 × 10¹⁸ FLOP
312000000000000*24*3600*0.3 = 8.08704e+18
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 8
- Chip-hours
- 24
- Power draw
- 6.3 kW
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (unrestricted)
- Training code
- Open source
MIT License https://github.com/MedARC-AI/MindEyeV2/tree/main
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
MindEye2 was published by Stability AI,Medical AI Research Center (MedARC),Princeton University,University of Minnesota,University of Sydney,University of Waterloo, in United Kingdom of Great Britain and Northern Ireland, in June 2024. industry,Research collective,Academia,Academia,Academia,Academia is the category the publisher falls under.
It works in Medicine, Vision, Image generation, and is recorded as doing image captioning, Image generation.
It builds on Stable Diffusion XL (SDXL), which is why it shares that model's general shape and size.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
Answers
MindEye2 — common questions
What GPU do I need to run MindEye2?
We cannot say. MindEye2 has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
Is MindEye2 open source?
Its weights are published, so MindEye2 can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does MindEye2 have?
No parameter count has been published for MindEye2, which is why no memory or speed figure appears on this page.
Who created MindEye2?
MindEye2 was published by Stability AI,Medical AI Research Center (MedARC),Princeton University,University of Minnesota,University of Sydney,University of Waterloo, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry,Research collective,Academia,Academia,Academia,Academia.
When was MindEye2 released?
MindEye2 was published in June 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is MindEye2 used for?
MindEye2 works in Medicine, Vision, Image generation, and is recorded as handling image captioning, Image generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
Where can I download MindEye2?
The weights for MindEye2 are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.