updating FID
Browse files
README.md
CHANGED
@@ -115,8 +115,8 @@ The following table compares our SPRIGHT-T2I model with SD 2.1 across multiple s
|
|
115 |
|
116 |
|Method |OA(%) β|VISOR-4(%) β|T2I-CompBench β|FID β|CCMD β|
|
117 |
|------------------|-------|------------|---------------|-----|------|
|
118 |
-
|SD v2.1 |47.83 |4.70 |0.1507 |
|
119 |
-
|SPRIGHT-T2I (ours)|60.68 |16.15 |0.2133 |
|
120 |
|
121 |
Our key findings are:
|
122 |
- Increased the Object Accuracy (OA) score by 26.86%, indicating that we are much better at generating objects mentioned in the input prompt
|
|
|
115 |
|
116 |
|Method |OA(%) β|VISOR-4(%) β|T2I-CompBench β|FID β|CCMD β|
|
117 |
|------------------|-------|------------|---------------|-----|------|
|
118 |
+
|SD v2.1 |47.83 |4.70 |0.1507 |21.646|1.060 |
|
119 |
+
|SPRIGHT-T2I (ours)|60.68 |16.15 |0.2133 |16.149|0.512 |
|
120 |
|
121 |
Our key findings are:
|
122 |
- Increased the Object Accuracy (OA) score by 26.86%, indicating that we are much better at generating objects mentioned in the input prompt
|