Victor Kuznetsov 2d5b26ed18 test(eval): vision-transcribed ground truth for qwen_in + clean text-CER numbers ...

data/qwen_in/ground_truth.json is transcribed by vision (PaddleOCR mangled the
stylized Cyrillic), so the text metric scores variants against an accurate
reference instead of noisy OCR-vs-OCR. Re-measured text CER (controlnet vs qwen)
with this ground truth confirms qwen wins text across EN/RU/ZH: openai_1 0.385 vs
0.241, openai_2 0.341 vs 0.290, gemini_1 (ZH) 0.037 vs 0.000 (perfect Chinese even
at the higher 0.30 strength). Faces still favor controlnet. Refresh the numbers in
docs/known-limitations.md to this cleaner methodology.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-20 14:26:23 -07:00

..

doubao_capture

feat(visible): add Jimeng remover, fix Doubao outline defect, reproducible mask build

2026-05-31 12:20:19 -07:00

gemini_capture

feat(visible): add Jimeng remover, fix Doubao outline defect, reproducible mask build

2026-05-31 12:20:19 -07:00

jimeng_capture

feat(visible): add Jimeng remover, fix Doubao outline defect, reproducible mask build

2026-05-31 12:20:19 -07:00

qwen_in

test(eval): vision-transcribed ground truth for qwen_in + clean text-CER numbers

2026-06-20 14:26:23 -07:00

samples

test(c2pa): add real FLUX.2 BFL C2PA fixtures (PNG + JPEG)

2026-06-19 09:37:40 -07:00

samsung_capture

feat(visible): Samsung Galaxy AI mark removal (bottom-left reverse-alpha, #37)

2026-06-05 10:27:44 -07:00

synthid_corpus

data(corpus): archive June 2026 SynthID strength-study subjects

2026-06-03 17:09:58 -07:00