# Reproduce the Doom render

Run stock Hugging Face inference first, from the bundle root:

```bash
python infer.py --model . --prompt examples/e1m1_prompt.txt --output out
```

The two following tools independently consume the raw tokenizer text. They
do not load the model and do not invoke one another:

```bash
python tools/pretty_text.py --input out/output.txt --output out/output.pretty.txt
python tools/txt_to_png.py  --input out/output.txt --output out/frame.png
```

`output.ids.json` is the canonical record of emitted model row ids;
`output.txt` is their standard-tokenizer interchange form.

The cursor/pixel token protocol these tools decode is specified in
`PROTOCOL.md` in the source repo (github.com/physicsrob/torchwright_doom).