Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,8 @@ tags:
|
|
7 |
- art
|
8 |
- image-to-text
|
9 |
- image-captioning
|
10 |
-
---
|
|
|
|
|
|
|
|
|
|
7 |
- art
|
8 |
- image-to-text
|
9 |
- image-captioning
|
10 |
+
---
|
11 |
+
|
12 |
+
# DALL路E 3 Image prompt reverse-engineering
|
13 |
+
|
14 |
+
Pre-trained image-captioning model BLIP fine-tuned on a mixture of `laion/dalle-3-dataset` and semi-automatically gathered `(image, prompt)` data from DALLE路E 3. It takes a generated image as an input and outputs a potential prompt to generate such an image, which can then be used as a base to generate similar images.
|