Text To Image Generation On Geneva Codraw
Metrics
F1-score
rsim
Results
Performance results of various models on this benchmark
Model Name | F1-score | rsim | Paper Title | Repository |
|---|---|---|---|---|
| LatteGAN | 77.51± 0.52 | 54.16± 0.21 | LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation | |
| GeNeVA-GAN | 58.83 | 35.41 | Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction |
0 of 2 row(s) selected.