| --- |
| license: mit |
| pipeline_tag: text-to-image |
| --- |
| |
| # PixelModel 🖼️ |
|
|
| A neural network where the weights **are** the image. |
|
|
| ## 📌 What is this? |
|
|
| `model.png` is not a picture — it *is* the model. |
|
|
| Every pixel encodes neural network weights. At inference, the PNG is decoded into weight matrices forming a tiny MLP. The prompt is embedded into a vector, and the model generates a 32×32 image. |
|
|
| Training directly optimizes pixel values via gradient descent until the PNG becomes the model itself. |
|
|
| --- |
|
|
| ## 🎨 Weight Encoding |
|
|
| - **R channel** → weight magnitude (0–255 → 0.0–1.0) |
| - **B channel** → weight sign (<128 = negative, ≥128 = positive) |
| - **G channel** → unused / reserved |
|
|
| --- |
|
|
| ## 🧠 Architecture |
|
|
| ```text |
| prompt string |
| → char embedding → 32-dim vector |
| → W1 (64×32) → tanh |
| → W2 (64×64) → tanh |
| → W3 (3072×64) → sigmoid |
| → reshape → 32×32×3 image |
| ```` |
|
|
| All weights live inside `model.png`. |
|
|
| --- |
|
|
| ## 🧪 Dataset vs Outputs |
|
|
| | Target | Output | |
| | ------------------------------------------ | -------------------------------------- | |
| | <img src="dataset/red.png" width="120"> | <img src="out_red.png" width="120"> | |
| | <img src="dataset/green.png" width="120"> | <img src="out_green.png" width="120"> | |
| | <img src="dataset/blue.png" width="120"> | <img src="out_blue.png" width="120"> | |
| | <img src="dataset/white.png" width="120"> | <img src="out_white.png" width="120"> | |
| | <img src="dataset/yellow.png" width="120"> | <img src="out_yellow.png" width="120"> | |
| | <img src="dataset/dark.png" width="120"> | <img src="out_dark.png" width="120"> | |
|
|
| --- |
|
|
| ## 📁 Files |
|
|
| ```text |
| model.png ← THE MODEL (64×3200 px) |
| main.py ← inference |
| train.py ← training |
| model.py ← architecture |
| dataset/ |
| red.png |
| red.txt ← prompt: "red" |
| ... |
| ``` |
|
|
| --- |
|
|
| ## ⚙️ Usage |
|
|
| ```bash |
| python train.py |
| python train.py --epochs 500 --lr 0.05 |
| |
| python main.py "red" |
| python main.py "a cat" --out cat.png --scale 8 |
| ``` |
|
|
| --- |
|
|
| ## 📊 Tips |
|
|
| * 6–20 samples are enough |
| * Simple patterns converge fastest |
| * 200–500 epochs typical |
| * Loss < 0.001 is strong for toy datasets |
|
|
| --- |
|
|
| *It’s a toy. It’s not useful. But it works.* |
|
|
| Bench Labs · Simple, Reliable, Open sourced |
|
|
