Text To Image Generation On Multi Modal
Metrics
Acc
FID
LPIPS
Real
Results
Performance results of various models on this benchmark
| Paper Title | |||||
|---|---|---|---|---|---|
| DFGAN | 17.3 | 137.60 | 0.581 | 14.5 | DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis |
| DM-GAN | 16.4 | 131.05 | 0.544 | 16.9 | DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis |
| AttnGAN | 13.0 | 125.98 | 0.512 | 11.9 | AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks |
| ControlGAN | 14.6 | 116.32 | 0.522 | 13.1 | Controllable Text-to-Image Generation |
| TediGAN-A | 18.4 | 106.37 | 0.456 | 22.6 | TediGAN: Text-Guided Diverse Face Image Generation and Manipulation |
| TediGAN-B | 20.4 | 101.42 | 0.461 | 21.0 | Towards Open-World Text-Guided Face Image Generation and Manipulation |
| Unite and Conquer | - | 26.09 | 0.519 | - | Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models |
| Corgi | - | 19.74 | - | - | Shifted Diffusion for Text-to-image Generation |
| Lafite | - | 12.54 | - | - | LAFITE: Towards Language-Free Training for Text-to-Image Generation |
| Swinv2-Imagen | - | 10.31 | - | - | Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation |
0 of 10 row(s) selected.