egeorcun
/

lucida

Image Segmentation

background-removal

text-preservation

Model card Files Files and versions

egeorcun commited on 3 days ago

Commit

4013af1

·

verified ·

1 Parent(s): a34eeda

v7 numbers

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -23,11 +23,12 @@ excel where most open models fail: **camouflaged objects, transparent materials
 (glass), text & logos, VFX glows, and illustrations** — while staying competitive
 everywhere else.
-On our 191-image, 8-category benchmark (MAE, lower is better) Lucida leads every
-model we tested — including a commercial reference — in **camouflage (0.0249)** and
-**illustration (0.0089)**, beats the commercial reference in **text/logo
-preservation (0.0112 vs 0.0123)**, and sets our best-ever **transparency-in-mixed-objects** handling and
-**overall (0.0303)** scores. Full benchmark, gallery and training recipe:
 **https://github.com/egeorcun/lucida** — or try the [live demo](https://huggingface.co/spaces/egeorcun/lucida-demo).
 ## Usage

 (glass), text & logos, VFX glows, and illustrations** — while staying competitive
 everywhere else.
+On our 203-image, 9-category benchmark (MAE, lower is better) Lucida leads every
+model we tested — including a commercial reference — in **camouflage (0.0270)** and
+**illustration (0.0092)**, beats the commercial reference in **text/logo
+preservation (0.0091 vs 0.0123)** and in **print-design/sticker art (0.0235 — 2x better
+than every model measured)**, and sets our best-ever **transparency-in-mixed-objects** handling and
+**overall (0.0257)** score — as of v7, ahead of every model we measured, specialist or commercial, on the 203-image average. Full benchmark, gallery and training recipe:
 **https://github.com/egeorcun/lucida** — or try the [live demo](https://huggingface.co/spaces/egeorcun/lucida-demo).
 ## Usage