Hugging Face's logo

SPRIGHT-T2I
/
spright-t2i-sd2

Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
Model card Files
xet
 Community
3

updating FID

#2
by agneet - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+2
-2
Files changed (1) hide show
  1. README.md +2 -2
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(%) ↑|VISOR-4(%) ↑|T2I-CompBench ↑|FID ↓|CCMD ↓|
117
  |------------------|-------|------------|---------------|-----|------|
118
- |SD v2.1 |47.83 |4.70 |0.1507 |27.39|1.060 |
119
- |SPRIGHT-T2I (ours)|60.68 |16.15 |0.2133 |27.82|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
 
115
 
116
  |Method |OA(%) ↑|VISOR-4(%) ↑|T2I-CompBench ↑|FID ↓|CCMD ↓|
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