Y2K DIGICAM LORA (2026)

Six standalone scripts. Each one reads the files the previous stage wrote and writes the files the next one reads. The zip is the input to fal.ai’s hosted krea-2-trainer.

scrape.py harvests 640px thumbnails from Wikimedia Commons “Taken with…” categories for eleven cameras — Nokia N95, Sony Ericsson Aino, C902, C905, and C702, Canon PowerShot A80, A70, and A95, Sony DSC-P200 and DSC-P8, Kodak EasyShare C743 — capped at 1,000 per category. A file is kept only if its license is CC0, public domain, CC BY, or CC BY-SA. An EXIF date outside 2003–2010 is rejected; a missing date is kept and flagged. Each kept file is a row in manifest.csv.

rank.py scores those thumbnails with SigLIP 2: mean cosine similarity to six candid, flash-lit, party-scene prompts minus mean similarity to six encyclopedic landmark prompts. The score is a sort order, written to scores.csv.

gallery.py writes one static HTML file, sorted by that score. A click cycles keep, reject, unmarked. Export downloads keepers.json. The committed cuts are 160 combined, 122 cameraphone, and 38 compact digicam.

fetch.py downloads the original for each keeper into data/fullres/, skipping files already on disk.

caption.py asks MiniCPM-V, served locally through Ollama, for the literal content and forbids style, camera, and era. A caption that is too short, or one word repeated past a fixed count and fraction, is rejected. A rejected or unreachable reply falls back to Qwen3-VL, which sees a 1024×1024 copy, reloads for every image, and starts each reply with one of six openers chosen from the filename. Sidecars are written as content plus a trigger. The default trigger is y2k digicam snapshot style.

package.py will not write the zip unless every keeper has an image and a caption sidecar. Beside the zip it writes an attribution CSV. Passing a keepers file and an output name packages one cut from the same full-resolution pool.