Text To Image Generation On Geneva I Clevr
평가 지표
F1-score
rsim
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | F1-score | rsim | Paper Title | Repository |
|---|---|---|---|---|
| GeNeVA-GAN | 88.39 | 74.02 | Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction | |
| LatteGAN | 97.26±1.56 | 83.21± 1.70 | LatteGAN: Visually Guided Language Attention for Multi-Turn Text-Conditioned Image Manipulation |
0 of 2 row(s) selected.