Text-to-Image Generation on Sampled color condition (Manual)
72.6FIDStable Diffusion
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Stable DiffusionEvaluation Protocol=Pre-train, Inference Cost=1.002025.03 | 72.6 | 27.3 | 166 | 65.3 | |
| Color-Aligned DiffusionEvaluation Protocol=Fine-tune, Conditioning Space=Latent, Inference Cost=1.032025.03 | 86.7 | 29 | 73.9 | 15.8 | |
| Color-Aligned DiffusionEvaluation Protocol=Zero-shot, Conditioning Space=Latent, Inference Cost=3.522025.03 | 104 | 28.3 | 35.2 | 3.19 | |
| ControlNet-ColorEvaluation Protocol=Baseline, Inference Cost=1.782025.03 | 105 | 22.9 | 129 | 49.8 | |
| T2I-AdapterEvaluation Protocol=Baseline, Inference Cost=1.562025.03 | 134 | 24.3 | 143 | 24.7 | |
| Style-AlignedEvaluation Protocol=Baseline, Inference Cost=5.692025.03 | 177 | 23.5 | 45.1 | 32.5 | |
| IP-AdapterEvaluation Protocol=Baseline, Inference Cost=1.442025.03 | 202 | 25.5 | 145 | 106 |