Image Generation on Multi-Modal-CelebA-HQ
Metric: FID (lower is better)
Metric: FID (lower is better)
| # | Model↕ | FID▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Swinv2-Imagen | 10.31 | No | Swinv2-Imagen: Hierarchical Vision Transformer D... | 2022-10-18 | - |
| 2 | Lafite | 12.54 | No | LAFITE: Towards Language-Free Training for Text-... | 2021-11-27 | Code |
| 3 | Corgi | 19.74 | No | Shifted Diffusion for Text-to-image Generation | 2022-11-24 | Code |
| 4 | Unite and Conquer | 26.09 | No | Unite and Conquer: Plug & Play Multi-Modal Synth... | 2022-12-01 | Code |
| 5 | TediGAN-B | 101.42 | No | Towards Open-World Text-Guided Face Image Genera... | 2021-04-18 | Code |
| 6 | TediGAN-A | 106.37 | No | TediGAN: Text-Guided Diverse Face Image Generati... | 2020-12-06 | Code |
| 7 | ControlGAN | 116.32 | No | Controllable Text-to-Image Generation | 2019-09-16 | Code |
| 8 | AttnGAN | 125.98 | No | AttnGAN: Fine-Grained Text to Image Generation w... | 2017-11-28 | Code |
| 9 | DM-GAN | 131.05 | No | DM-GAN: Dynamic Memory Generative Adversarial Ne... | 2019-04-02 | Code |
| 10 | DFGAN | 137.6 | No | DF-GAN: A Simple and Effective Baseline for Text... | 2020-08-13 | Code |