Text-to-Image Generation on ShareGPT4V (val)
0.317FIDDeBias-CLIP
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DeBias-CLIPBase Generative Model=SDXL2026.02 | 0.317 | 0.528 | |
| Long-CLIPBase Generative Model=SDXL2026.02 | 0.335 | 0.515 |
| Method | Links | ||
|---|---|---|---|
| DeBias-CLIPBase Generative Model=SDXL2026.02 | 0.317 | 0.528 | |
| Long-CLIPBase Generative Model=SDXL2026.02 | 0.335 | 0.515 |