Columba1198
/

EgaraNet

Image Feature Extraction

feature-extraction

vision-transformer

custom-architecture

Model card Files Files and versions

Columba1198 commited on Apr 11

Commit

ad8abb7

·

verified ·

1 Parent(s): f235525

Upload folder using huggingface_hub

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ EgaraNet is an embedding model that encodes the artistic style of illustrations
 |---|---|
 | **Architecture** | DINOv3 ViT-L/16 backbone + StyleNet (Transposed Attention Transformer) head |
 | **Embedding Dim** | 1024 |
-| **Input** | RGB images, any resolution (multiples of 16 recommended) |
 | **Output** | L2-normalized style embedding vector |
 | **Training Data** | ~1.2M illustrations from ~12K artists |

 |---|---|
 | **Architecture** | DINOv3 ViT-L/16 backbone + StyleNet (Transposed Attention Transformer) head |
 | **Embedding Dim** | 1024 |
+| **Input** | RGB images, any resolution (must be a multiple of 16) |
 | **Output** | L2-normalized style embedding vector |
 | **Training Data** | ~1.2M illustrations from ~12K artists |