| --- |
| title: PixelLock |
| emoji: 🎨 |
| colorFrom: purple |
| colorTo: indigo |
| sdk: docker |
| app_port: 7860 |
| pinned: true |
| license: gemma |
| short_description: Footprint-locked AI pixel-art retexturing |
| models: |
| - solarkyle/pixellock-gemma-12b-pixelart-gguf |
| tags: |
| - gradio |
| - build-small-hackathon |
| - track:wood |
| - achievement:offbrand |
| - achievement:welltuned |
| - achievement:llama |
| - achievement:sharing |
| - achievement:fieldnotes |
| - achievement:offgrid |
| - best-demo |
| - bonus-quest-champion |
| - pixel-art |
| --- |
| |
| # 🎨 PixelLock — AI Pixel-Art Retexturing |
|
|
| Upload a sprite, pick a vibe (or write your own), hit **Run**. PixelLock restyles |
| the colors and shading while keeping the **exact silhouette** — pixel-perfect, |
| *guaranteed by construction*. |
|
|
| > ⏳ This is a GPU Space that auto-sleeps. The first visit cold-starts the model |
| > (~30–60s). If the first edit errors, the model is still waking — try again. |
|
|
| ## 🔗 Links |
|
|
| - 🎥 **Demo video:** [WATCH ▶](VIDEO_LINK) |
| - 📣 **Social post:** [SEE POST](SOCIAL_POST_LINK) |
| - 🧠 **Model (fine-tuned GGUF):** https://huggingface.co/solarkyle/pixellock-gemma-12b-pixelart-gguf |
| - 📄 **Full technical writeup:** [read it](WRITEUP_LINK) |
|
|
| ## The idea: the *wrong* model on purpose |
|
|
| PixelLock does **not** use an image generator. It uses a **fine-tuned text LLM** |
| (Gemma-4-12B). The sprite is serialized to a tiny text wire — a `PALETTE` block |
| plus a `GRID` of space-separated cells — and the model **rewrites that text** in a |
| new style. The trick is a per-sprite **GBNF decoding grammar** (llama.cpp): every |
| transparent cell is pinned to a fixed literal, so the model is *physically |
| incapable* of moving a pixel. The footprint and transparency are preserved **by |
| construction**, not by luck. It's language modeling, not diffusion — and that's |
| exactly why the shape can never break. |
|
|
| In a benchmark, *no* model could emit a correct 32×32 grid unconstrained |
| (~0/150 attempts); the grammar takes validity from **0% → 100%** at every size |
| (16×16 → 128×128, incl. 2× upscale), footprint-perfect every time. |
|
|
| ## The tech |
|
|
| - **Fine-tuned model** — QLoRA fine-tune of Gemma-4-12B on a curated corpus of |
| palette-indexed pixel-art sprites (≤64px); completion-only loss, |
| step-checkpointing, final eval loss **0.378**. Exported to GGUF (q4_k_m). |
| - **Grammar-constrained decoding** — a per-sprite GBNF grammar compiled from the |
| input footprint; the silhouette is locked in the decoder, not post-filtered. |
| - **Custom Gradio UI** — a heavily themed `gr.Blocks` interface (Off-Brand) that |
| builds the grammar per upload, footprint-checks the output, and shows you the |
| **raw text the model wrote**. |
| - **Serving** — Docker GPU Space running llama.cpp `llama-server` (CUDA) with the |
| per-request grammar; auto-sleeps when idle. |
|
|
| Built for the **Build Small** hackathon · *Thousand Token Wood* track. |
|
|
