updated documente
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Model weights for executing the mangaka cli.
|
| 2 |
+
|
| 3 |
+
The models are ONNX exports of various checkpoints.
|
| 4 |
+
## usage
|
| 5 |
+
- the sam models are for bubble speech detection
|
| 6 |
+
- the ocr models are for character recognition
|
| 7 |
+
- dbconvnext is used for text box recognition
|
| 8 |
+
- lama is for impatingin
|
| 9 |
+
|
| 10 |
+
## licensing
|
| 11 |
+
The SAM models are under the SAM license, and the other models are covered under their appropriate exports.
|
| 12 |
+
https://github.com/facebookresearch/sam3/blob/main/LICENSE
|
| 13 |
+
|
| 14 |
+
The models otherwise are otherwise not licensable properly since its all documented as model weights, which aren't necessarily code, so assume CC-BY?
|
| 15 |
+
- dbconvnext (https://github.com/zyddnys/manga-image-translator/) - GPL
|
| 16 |
+
- ocr-48px (https://github.com/zyddnys/manga-image-translator/) - GPL
|
| 17 |
+
- lama (https://huggingface.co/Carve/LaMa-ONNX) - Apache
|