old_readme.md

---
license: creativeml-openrail-m
tags:
- controlnet
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
---

# This model is in an unfinished state for now


## Controlnet model for use in qr codes sdxl

Conditioning only 25% of the pixels closest to black and the 25% closest to white.

v0.1-unfinished requires a high Control Weight (arround 1.4)

TODO:
* fix the files naming
* update the readme
* sleep 8 hours


![image/png](https://cdn-uploads.huggingface.co/production/uploads/62fb24dc86456e533456ebd1/HuySQrjRTfhssxWm4ZU3g.png)

# Not yet scannable

![image/png](https://cdn-uploads.huggingface.co/production/uploads/62fb24dc86456e533456ebd1/pM8bk7QLP6QMJ2PfxRlWj.png)


# I am working on two versions, one more oriented to make qr readable (like the original qr pattern), and the other more oriented to optical illusions
## this is an example of the second version:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/62fb24dc86456e533456ebd1/774wi5C_VMSkdOA14oDG4.png)


![image/png](https://cdn-uploads.huggingface.co/production/uploads/62fb24dc86456e533456ebd1/e9ItY6UCneiYx-B6AYu7p.png)

QR Pattern and QR Pattern sdxl were created as free community resources by an Argentinian university student. Training AI models requires money, which can be challenging in Argentina's economy.
If you find these models helpful and would like to empower an enthusiastic community member to keep creating free open models, I humbly welcome any support you can offer through ko-fi here.
https://ko-fi.com/nacholmo