History

jamestagg 72d57eefd2 Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks 40 new maps, imported meshes, Fab camping/medieval tents, WaterMill, Street, Starship, bateaux training references, benchmark sky references, GeneratedAssets Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-20 13:09:23 -07:00
..
The best boats to explore Paris from _ Bateaux Mouches®_files	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
sunsets	Add rope bridge, new maps, imported meshes, training sets, benchmark	2026-03-17 10:27:40 -07:00
Chochedeau.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Correlle.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Flute.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Galiote.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Garabouche.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Hirondelle.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Jean-Bruel.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Jean-Sebastian.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Lespoire.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Palanche.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
README.md	Add rope bridge, new maps, imported meshes, training sets, benchmark	2026-03-17 10:27:40 -07:00
The best boats to explore Paris from _ Bateaux Mouches®.html	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
Zouave.jpeg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux front.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux night.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux open top.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux round.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux sharp night.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux sharp.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux square.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00
bateaux.jpg	Add new maps, Fab assets, WaterMill, Street, Starship, training sets, benchmarks	2026-03-20 13:09:23 -07:00

README.md

Training Sets

Brain training reference images organized by domain. All images are CC0 / public domain.

Directory Structure

training_sets/
├── sunsets/       ← SKY domain: sunset, golden hour, sky gradients
├── oceans/        ← SEA domain: ocean, waves, coastal
├── food/          ← FOOD domain: food photography, plating
├── portraits/     ← PORTRAIT domain: people, faces, characters
├── urban/         ← URBAN domain: city, architecture, streets
├── nature/        ← NATURE domain: mountains, forests, landscapes
└── weather/       ← WEATHER domain: fog, rain, snow, storms

Usage

From the ralpha repo:

# Run batch training on a domain
python -m brain.batch --dir /path/to/ralpha-ue5/training_sets/sunsets/ \
  --domain SKY --llm gemini --max-iterations 20 --shuffle

# Or symlink for convenience
ln -s /path/to/ralpha-ue5/training_sets ~/ralpha/training_sets

Sourcing Images

# Download CC0 sunset images (PxHere, with EXIF)
cd /path/to/ralpha
python scripts/dev/download_training_sunsets.py --output /path/to/ralpha-ue5/training_sets/sunsets/

EXIF Data

Images with intact EXIF are preferred — the brain extracts:

Camera model + lens → locks CineCamera focal length, aperture
Date/time → computes exact sun position via ephemeris
GPS → loads Cesium tiles for that location, locks sun azimuth
ISO/aperture/shutter → exposure starting point

Images without EXIF still work — the brain uses VLM analysis to estimate scene parameters.

Licensing

All images in this directory must be CC0 (Creative Commons Zero) or public domain. The manifest.json in each subdirectory records the source and license of each image.