Class Conditional Image Generation on ImageNet 256x256 1k (train val)
2.27FIDDiT-XL/2-G
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DiT-XL/2-GTotal Images(M)=1792, Total Gflops=2.13 x 10^11, Classifier-free Guidance=true2023.11 | 2.27 | 4.6 | 278.24 | 83 | 57 | |
| DIFFUSSM-XL-GTotal Images(M)=660, Total Gflops=1.85 x 10^11, Classifier-free Guidance=true2023.11 | 2.28 | 4.49 | 259.13 | 86 | 56 | |
| U-ViT-H/2-GTotal Images(M)=512, Total Gflops=6.81 x 10^10, Classifier-free Guidance=true2023.11 | 2.29 | — | 247.67 | 87 | 48 | |
| StyleGAN-XLClassifier-free Guidance=false2023.11 | 2.3 | 4.02 | 265.12 | 78 | 53 | |
| ADM-G, ADM-UTotal Images(M)=507, Total Gflops=3.76 x 10^12, Classifier-free Guidance=true2023.11 | 3.6 | — | 247.67 | 87 | 48 | |
| LDM-4-GTotal Images(M)=213, Total Gflops=2.22 x 10^10, Classifier-free Guidance=true2023.11 | 3.95 | — | 178.22 | 81 | 55 | |
| ADM-GTotal Images(M)=507, Total Gflops=5.68 x 10^11, Classifier-free Guidance=true2023.11 | 4.59 | 5.25 | 186.7 | 82 | 52 | |
| CDMClassifier-free Guidance=false2023.11 | 4.88 | — | 158.71 | — | — | |
| MaskGITTotal Images(M)=355, Classifier-free Guidance=false2023.11 | 6.18 | — | 182.1 | 80 | 51 | |
| BigGAN-deepClassifier-free Guidance=false2023.11 | 6.95 | 7.36 | 171.4 | 87 | 28 | |
| ADM-UTotal Images(M)=507, Total Gflops=3.76 x 10^11, Classifier-free Guidance=false2023.11 | 7.49 | 5.13 | 127.49 | 72 | 63 | |
| LDM-8-GTotal Images(M)=307, Total Gflops=1.75 x 10^10, Classifier-free Guidance=true2023.11 | 7.76 | — | 209.52 | 84 | 35 | |
| DIFFUSSM-XLTotal Images(M)=660, Total Gflops=1.85 x 10^11, Classifier-free Guidance=false2023.11 | 9.07 | 5.52 | 118.32 | 69 | 64 | |
| DiT-XL/2Total Images(M)=1792, Total Gflops=2.13 x 10^11, Classifier-free Guidance=false2023.11 | 9.62 | 6.85 | 121.5 | 67 | 67 | |
| LDM-4Total Images(M)=213, Total Gflops=2.22 x 10^10, Classifier-free Guidance=false2023.11 | 10.56 | — | 103.49 | 71 | 62 | |
| ADMTotal Images(M)=507, Total Gflops=5.68 x 10^12, Classifier-free Guidance=false2023.11 | 10.94 | 6.02 | 100.98 | 69 | 63 | |
| LDM-8Total Images(M)=307, Total Gflops=1.75 x 10^10, Classifier-free Guidance=false2023.11 | 15.51 | — | 79.03 | 65 | 63 |