eDiff-I
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
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
- NVIDIA
- Organisation type
- Industry
- Country
- United States of America
- Published
- 2 November 2022
- Authors
- Yogesh Balaji, Seungjun Nah, Xun Huang, Arash Vahdat, Jiaming Song, Qinsheng Zhang, Karsten Kreis, Miika Aittala, Timo Aila, Samuli Laine, Bryan Catanzaro, Tero Karras, Ming-Yu Liu
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Image generation, Text-to-image
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.
- Parameters
- 9.1B
- Training data
- 1,556,275,200,000 tokens
9.1B for config D, Table 1
"The final dataset to train our model contains about one billion text-image pairs"
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.
- Training compute
- 5.5 × 10¹⁹ FLOP
- How it was established
- Operation counting
6ND = 6*9100000000*1000000000=5.46e+19 (likely, might change because of several epochs / dataset division) "The base model was trained using 256 NVIDIA A100 GPUs, while the two super-resolution models were trained with 128 NVIDIA A100 GPUs each" no info on duration
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
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
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Likely
- Citations
- 1,046
SOTA zero-shot FID on COCO 2014, Table 1 May be significantly used, via Nvidia Picasso: https://www.nvidia.com/en-us/gpu-cloud/picasso/
Sources
Where this record came from and when it was last checked.
- Reference
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
- Last updated
- 25 May 2026
What the numbers mean
About this model
eDiff-I was published by NVIDIA, in the country recorded as United States of America, during November 2022. The publishing organisation is categorised as industry.
It works in the domain of Image generation, and is recorded as performing the task of image generation, Text-to-image.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
Training it took a computation budget of roughly 5.5 × 10¹⁹ FLOP, on hardware recorded as NVIDIA A100. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 1,556,275,200,000 tokens of text.
Its inclusion criterion: sOTA improvement.
Answers
eDiff-I — common questions
eDiff-I— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
eDiff-I— how many parameters does it have?
It has a parameter count of 9.1B. 9.1B for config D, Table 1. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
eDiff-I— who created it?
It was published by NVIDIA, based in United States of America, an organisation categorised as industry.
eDiff-I— when was it released?
It was published in November 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
eDiff-I— what is it used for?
It works in the domain of Image generation, and is recorded as handling the task of image generation, Text-to-image. 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.
eDiff-I— how much compute was used to train it?
Training consumed around 5.5 × 10¹⁹ FLOP, on hardware recorded as NVIDIA A100. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
eDiff-I— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
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.