| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Conditional Generation | Controllable generation dataset ControlNet-supported 1.0 | Self-sim0.134 | 8 | |
| Style and Content-conditioned image generation | Controllable Generation Dataset Style;Content (test) | CLIP Score0.2402 | 4 | |
| Segmentation map-conditioned image generation | Controllable Generation Dataset (test) | CLIP Score0.254 | 4 | |
| Depth map-conditioned image generation | Controllable Generation Dataset Depth (test) | CLIP Score0.2561 | 4 | |
| Human pose-conditioned image generation | Controllable Generation Dataset Pose (test) | CLIP Score0.2608 | 4 | |
| Canny edge-conditioned image generation | Controllable Generation Dataset Canny (test) | CLIP Score0.2539 | 4 | |
| HED boundary-conditioned image generation | Controllable Generation Dataset HED (test) | CLIP Score0.2556 | 3 |