Update README.md
Browse files
README.md
CHANGED
|
@@ -12,4 +12,10 @@ The caption (prompt) was tokenized by [ModernBERT](https://huggingface.co/answer
|
|
| 12 |
|
| 13 |
*Image-Caption Similarity Scoring*: The model assigns a score to each image based on how closely it is related to its associated caption.
|
| 14 |
|
| 15 |
-
*Image Labeling*: The image embedding is used to label images by color and character name.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
*Image-Caption Similarity Scoring*: The model assigns a score to each image based on how closely it is related to its associated caption.
|
| 14 |
|
| 15 |
+
*Image Labeling*: The image embedding is used to label images by color and character name.
|
| 16 |
+
|
| 17 |
+
## Updates
|
| 18 |
+
|
| 19 |
+
The 1.2 and 1.3 versions focused on the heads, clothes, and colors of the most common anime characters.
|
| 20 |
+
|
| 21 |
+
Moving forward, the uploads will focus on rare characters, with only a few samples.
|