--- license: apache-2.0 library_name: pytorch pipeline_tag: text-to-image tags: - pixel-art - sprite-generation - text-to-image --- # Pixie P32 (pixie-32) A 66M-parameter autoregressive model that paints native 32×32 palette-indexed pixel-art sprites from a short text prompt. Code, training pipeline and sampler: [github.com/QuarkOS/pixie](https://github.com/QuarkOS/pixie). Sibling model: [EmilioSchwaiger/pixie-16](https://huggingface.co/EmilioSchwaiger/pixie-16). Files: `model.safetensors` (weights), `config.json` (architecture), `palette.npy` (4097×3 uint8 palette; index 0 is transparent). ![Samples: red potion, iron helmet, green slime (4 each, seed 0, CFG 2.0)](sample.png) ## Model | Field | Value | | --- | --- | | Name | Pixie P32 (`pixie-32`) | | Version | Best checkpoint of the first full P32 run: step 17,746, about 1.25M training images seen | | Architecture | P32: autoregressive transformer over palette indices. Width 512, 16 layers, 8 heads, 2×2 patch tokens (256 patches of four palette slots), partial axial 2D-RoPE, three palette slots and one style slot. See the README. | | Parameters | 66,424,320 (counted from the released `model.safetensors`; 224 float32 tensors) | | Checkpoint SHA256 | `1a26888728f3c523075f691e4fddb270889e0a4db814c516da016709a06b9dbc` (`model.safetensors`) | | Output | One 32×32 RGBA sprite per sample; index 0 is transparent | | Text encoder | External, not shipped: the first 11 layers of the [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) text model (penultimate features, 18 positions) | | Intended use | Generate palette-indexed pixel-art game sprites (items, weapons, characters, creatures, props) from a short English prompt. | | Out of scope | Photoreal images, text rendering, anything larger than 32×32, and subjects far outside game-sprite content. | ## Training data | Field | Value | | --- | --- | | Training set | About 130k native 32×32 sprites generated for this project with Krea 2 Turbo plus a pixel-art LoRA, cut from 3×3 sheets by `data-pipeline/extract_v2.py`. Not released. | | License of the data | The generated sprites are Krea 2 Outputs, owned by their generator per section 5.3 of the [Krea 2 Community License](https://github.com/krea-ai/krea-2/blob/main/docs/KREA-2-COMMUNITY-LICENSE). See [NOTICE](NOTICE). | | Holdouts excluded | The Blind-50 and Eval-50 phrase lists were excluded from training by the builder's frozen-holdout check. The lists themselves are not published. | | Personal data | None in the weights files. Captions are the generation prompts. | ## Weights license | Field | Value | | --- | --- | | License | Apache-2.0, the same as the code. See [LICENSE](LICENSE) and [NOTICE](NOTICE). | | Inherited restrictions | None claimed. No Krea or CLIP weights are part of the release; CLIP (MIT) is downloaded separately at sampling time. | ## Evaluation | Field | Value | | --- | --- | | IID validation NLL | 0.5237 at the released step (lowest of the run, which is why this checkpoint was kept) | | Blind-50 / Eval-50 | Not reported as a number for this release. | ## Known limitations - Stray magenta pixels: the training sheets used a magenta key background, and some samples keep a few magenta background-key pixels near the edges. - The run overfits after about 1.25M images; later checkpoints were worse on IID NLL, so this is not the last checkpoint of the run. - Needs the external CLIP ViT-L/14 text encoder, which is linked, not shipped. - Quality varies by subject; many samples are rough. Treat it as a small research model, not a finished asset generator. ## How to sample ```bash git clone https://github.com/QuarkOS/pixie && cd pixie python3 -m venv .venv && . .venv/bin/activate pip install torch numpy pillow tokenizers safetensors huggingface_hub hf download EmilioSchwaiger/pixie-32 --local-dir pixie-32 hf download openai/clip-vit-large-patch14 model.safetensors tokenizer.json --local-dir clip-vit-large-patch14 python -m train.sample_pixie --model-dir pixie-32 \ --clip clip-vit-large-patch14/model.safetensors \ --tokenizer clip-vit-large-patch14/tokenizer.json \ --prompt "red potion" --prompt "iron helmet" --n 4 --out sprites.png ``` Each row of `sprites.png` is one prompt (32×32 sprites, upscaled with nearest-neighbour). ## License Apache-2.0 for the weights. See [LICENSE](LICENSE) and [NOTICE](NOTICE) (Krea 2 attribution and third-party credits).