Text To Image Generation On Cub
評価指標
FID
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | FID |
|---|---|
| truncated-diffusion-probabilistic-models | 6.72 |
| controllable-text-to-image-generation | - |
| mirrorgan-learning-text-to-image-generation | - |
| galip-generative-adversarial-clips-for-text | 10.08 |
| learning-what-and-where-to-draw | 67.22 |
| attngan-fine-grained-text-to-image-generation | - |
| improving-text-to-image-synthesis-using | 16.34 |
| vector-quantized-diffusion-model-for-text-to | 10.32 |
| lafite-towards-language-free-training-for | 10.48 |
| stackgan-realistic-image-synthesis-with | 15.3 |
| swinv2-imagen-hierarchical-vision-transformer | 9.78 |
| vector-quantized-diffusion-model-for-text-to | 12.97 |
| stackgan-realistic-image-synthesis-with | 51.89 |
| dm-gan-dynamic-memory-generative-adversarial | - |
| data-extrapolation-for-text-to-image | 6.36 |
| stackgan-text-to-photo-realistic-image | - |
| vector-quantized-diffusion-model-for-text-to | 11.94 |
| recurrent-affine-transformation-for-text-to | 10.21 |
| improving-text-to-image-synthesis-using | 14.38 |
| df-gan-deep-fusion-generative-adversarial | - |