Update README.md
Browse files
README.md
CHANGED
|
@@ -17,9 +17,7 @@ expert comparisons, based on text prompts and corresponding model outputs from D
|
|
| 17 |
ImageReward outperforms existing text-image scoring methods, such as CLIP, Aesthetic, and BLIP, in terms of
|
| 18 |
understanding human preference in text-to-image synthesis through extensive analysis and experiments.
|
| 19 |
|
| 20 |
-
|
| 21 |
-
<img src="ImageReward.png" width="700px">
|
| 22 |
-
</p>
|
| 23 |
|
| 24 |
## Quick Start
|
| 25 |
|
|
|
|
| 17 |
ImageReward outperforms existing text-image scoring methods, such as CLIP, Aesthetic, and BLIP, in terms of
|
| 18 |
understanding human preference in text-to-image synthesis through extensive analysis and experiments.
|
| 19 |
|
| 20 |
+
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Quick Start
|
| 23 |
|