| --- |
| license: mit |
| pipeline_tag: text-to-image |
| language: |
| - en |
| tags: |
| - image |
| - t2i |
| - text-to-image |
| - custoom-code |
| model-index: |
| - name: PixelModel |
| results: |
| - task: |
| type: text-to-image |
| dataset: |
| name: fid |
| type: fid |
| metrics: |
| - name: fid |
| type: fid |
| value: 566.84 |
| - task: |
| type: text-to-image |
| dataset: |
| name: clip |
| type: clip |
| metrics: |
| - name: clip |
| type: clip |
| value: 0.186 |
| new_version: bench-labs/pixelmodel-v1 |
| --- |
| |
| <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> |
|
|
| </td> |
| </tr> |
| </table> |
|
|
| # 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`. |
|
|
| --- |
|
|
| ## 📦 Standard weights (safetensors) |
|
|
| `model.png` is the canonical model — training writes to it directly, and it's what makes PixelModel PixelModel. For tooling that expects standard weight files, the same 3 matrices are also exported as `model.safetensors` (202,752 parameters total, no bias terms): |
|
|
| ```bash |
| python convert_to_safetensors.py # model.png -> model.safetensors |
| python convert_to_safetensors.py --model model.png --out model.safetensors |
| ``` |
|
|
| Re-run this after training if you retrain into a new `model.png` — `model.safetensors` doesn't update itself. |
|
|
| Parameter count is verifiable two ways without running any code: `config.json` (`total_parameters: 202752`, full per-layer breakdown) and the safetensors file's own header metadata (`total_parameters`, `param_breakdown`, `has_bias`, `text_encoder_parameters`, `vae_parameters` — all 0 except the MLP itself). |
|
|
| --- |
|
|
| ## 🧪 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) |
| model.safetensors ← same weights, standard format (generated, see below) |
| config.json ← architecture + parameter-count metadata |
| main.py ← inference, loads model.png |
| INFERENCE.py ← inference, loads model.safetensors |
| convert_to_safetensors.py ← model.png -> model.safetensors |
| 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 |
| |
| # equivalent, but loads model.safetensors instead of model.png |
| python convert_to_safetensors.py |
| python INFERENCE.py "a cat" --out cat.png --scale 8 |
| ``` |
|
|
| `main.py` and `INFERENCE.py` produce byte-identical output for the same prompt — they're the same architecture and weights, just loaded from different files. |
|
|
| --- |
|
|
| ## 📊 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 |
