CogView2
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
- Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI
- Organisation type
- Academia,Academia
- Country
- China
- Published
- 28 April 2022
- Authors
- Ming Ding, Wendi Zheng, Wenyi Hong, Jie Tang
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
- 6B
- Training data
- 629,145,600,000 tokens
The backbone of our pretrained CogLM is a Transformer with Sandwich LayerNorm [3]. The model has 6 billion parameters (48 layers, hidden size 3072, 48 attention heads)
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
- 2.3 × 10²² FLOP
- How it was established
- Operation counting
"The model has 6 billion parameters (48 layers, hidden size 3072, 48 attention heads), trained for 300,000 iterations in FP16 with batch size 4,096" Using 6ND formula: 6*6000000000*300000*4096*512=2.2649242e+22
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers
- Last updated
- 28 November 2025
What the numbers mean
What this model is
CogView2 was published by Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI, in China, in April 2022. It comes out of academia,Academia.
It works in Image generation, and is recorded as doing image generation, Text-to-image.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Training it took roughly 2.3 × 10²² FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
It was trained on about 629,145,600,000 tokens of text.
Answers
CogView2 — common questions
Is CogView2 open source?
The licensing for CogView2 was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does CogView2 have?
CogView2 has 6B parameters. The backbone of our pretrained CogLM is a Transformer with Sandwich LayerNorm [3]. The model has 6 billion parameters (48 layers, hidden size 3072, 48 attention heads). 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.
Who created CogView2?
CogView2 was published by Tsinghua University,Beijing Academy of Artificial Intelligence / BAAI, based in China, categorised as academia,Academia.
When was CogView2 released?
CogView2 was published in April 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.
What is CogView2 used for?
CogView2 works in Image generation, and is recorded as handling image generation, Text-to-image. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train CogView2?
Around 2.3 × 10²² FLOP. 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.
What GPU do I need to run CogView2?
None. CogView2 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.