# Pepe Creation Process
\
tl;dr: We’ve sacrificed several thousands of Pepe the Frog images to the Neural God, who, in exchange has bestowed upon us 7,777 impeccable Neural Pepe.\
\
That’s how our neural artist described the generation process:
Translation from Russian:\
\
\&#xNAN;*“That’s how Pepe were created:*\
\
*Neural Pepe were generated using the* [*StyleGAN2*](https://github.com/NVlabs/stylegan2-ada) *generative adversarial network. The dataset consisted of over 7,000 different Pepe the Frog arts. The final collection includes models of different iterations to make the result more diverse. Each Neural Pepe NFT has a set of traits of different rarity. All traits were assigned using custom-made classifiers and then double-checked manually.*\
*No idea what else to say.*
*My hungover head refuses to work.”*
StyleGAN is a novel[ **generative adversarial network**](https://en.wikipedia.org/wiki/Generative_adversarial_network) **(GAN)** introduced by[ Nvidia](https://en.wikipedia.org/wiki/Nvidia) researchers
\
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.neuralpepe.com/neural-pepe-on-bnbchain/pepe-creation-process.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.