Multi-frame visual story generation on ConsiStory+
90.74CLIP-TVanilla SDXL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Vanilla SDXLBase model=SDXL, Steps=50, Memory (GB)=16.04, Inference Time (s)=13.0892026.02 | 90.74 | 81.65 | 52.92 | |
| ReDiStoryBase model=SDXL, Steps=50, Memory (GB)=18.89, Inference Time (s)=23.64132026.02 | 89.66 | 91.49 | 19.52 | |
| 1Prompt1StoryBase model=SDXL, Steps=50, Memory (GB)=18.7, Inference Time (s)=23.20882026.02 | 89.42 | 91.17 | 19.93 | |
| StoryDiffusionBase model=SDXL, Steps=50, Memory (GB)=45.61, Inference Time (s)=25.69282026.02 | 88.77 | 87.55 | 32.12 | |
| ConsiStoryBase model=SDXL, Steps=50, Memory (GB)=34.55, Inference Time (s)=34.58942026.02 | 87.69 | 87.37 | 31.88 | |
| PhotoMakerBase model=SDXL, Steps=50, Memory (GB)=23.79, Inference Time (s)=18.02592026.02 | 86.51 | 84.65 | 39.96 | |
| IP-AdapterBase model=SDXL, Steps=30, Memory (GB)=19.39, Inference Time (s)=13.45942026.02 | 84.58 | 94.29 | 14.62 | |
| Naive Prompt Reweighting (NPR)Base model=SDXL, Steps=50, Memory (GB)=16.04, Inference Time (s)=17.24132026.02 | 84.11 | 89.16 | 25.48 | |
| Textual InversionBase model=SD1.5, Steps=40, Memory (GB)=32.94, Inference Time (s)=282.5072026.02 | 83.78 | 82.29 | 42.68 | |
| Vanilla SD1.5Base model=SD1.5, Steps=50, Memory (GB)=4.73, Inference Time (s)=2.46572026.02 | 83.53 | 74.74 | 58.73 | |
| The Chosen OneBase model=SDXL, Steps=35, Memory (GB)=10.93, Inference Time (s)=11.20732026.02 | 76.14 | 78.31 | 49.29 | |
| BLIP-DiffusionBase model=SD1.5, Steps=26, Memory (GB)=7.75, Inference Time (s)=1.92842026.02 | 76.07 | 88.63 | 28.3 |