Table 1 Comparison of different generated images based on CLIP Score, LPIPS, FID, VTC, ASL, AP, and creativeness
From: A novel flexible identity-net with diffusion models for painting-style generation
CLIP Score \(\uparrow\) | LPIPS \(\downarrow\) | FID \(\downarrow\) | VTC \(\uparrow\) | ASL \(\uparrow\) | AP \(\uparrow\) | Creativeness \(\uparrow\) | |
|---|---|---|---|---|---|---|---|
DALL-E 367 | 0.6942 | 0.6727 | 3089 | 12.1% | 9.1% | 4.5% | 3.0% |
Midjourney68 | 0.7941 | 0.7584 | 2213 | 12.1% | 6.1% | 19.7% | 13.6% |
Midjourney + reference68 | 0.7133 | 0.7339 | 2313 | 7.6% | 3.0% | 12.1% | 10.6% |
DreamWorks Diffusion45 | 0.7776 | 0.7377 | 2726 | 4.6% | 7.6% | 1.5% | 7.6% |
PuLID-FLUX69 | 0.7853 | 0.7462 | 3022 | 3.0% | 6.1% | 9.1% | 9.1% |
PDANet (Ours) | 0.8147 | 0.5519 | 2037 | 60.6% | 68.2% | 53.0% | 56.1% |
