---
license: mit
pipeline_tag: text-to-image
language:
- en
tags:
- image
- t2i
- text-to-image
- custom-code
- tiny
model-index:
- name: PixelModel-v2
  results:
  - task:
      type: text-to-image
    dataset:
      name: fid
      type: fid
    metrics:
    - name: fid
      type: fid
      value: 390.68
  - task:
      type: text-to-image
    dataset:
      name: clip
      type: clip
    metrics:
    - name: clip
      type: clip
      value: 20.48
new_version: bench-labs/PixelModel-v3
---

<table align="center">
<tr>
<td align="center">

<a href="https://huggingface.co/spaces/bench-labs/BenchLabs-Leaderboard">🏆 BenchLabs Leaderboard</a> •
<a href="https://huggingface.co/spaces/FlameF0X/Tiny-T2I-Leaderboard">🌍 Tiny-T2I Leaderboard</a> •
<a href="https://huggingface.co/spaces/bench-labs/blog?post=Pm2and3.html">📝 Blog Post</a>

</td>
</tr>
</table>

# PixelModel v2 🖼️

<img src="model.png" alt="The entire PixelModel v1: a 160x149 PNG containing all 23,747 weights" style="image-rendering: pixelated; width: 320px; max-width: 100%;">


A neural network where the weights **are** the image. Scaled up.

Consider looking at previous versions for more context.

23k parameters -> 200k parameters (thats the only change)

## demo images

![image](https://cdn-uploads.huggingface.co/production/uploads/6471b447a2b0a376b8b5e879/I69aKAhFqW8Ungh89K80S.png)