Table 8

Inconsistency and intrinsic difficulty for different guidance scales and number of diffusion steps for Stable Diffusion 3. Classification error rate and obtained with Dual Vision Transformer –DaViT– model.

Diffusion steps/Guidance24812163264
0.53.49%2.55%2.38%2.32%2.49%2.53%3.33%
13.40%2.48%2.34%2.31%2.44%2.48%3.27%
23.33%2.44%2.31%2.34%2.41%2.50%3.22%
33.31%2.44%2.36%2.43%2.57%3.27%3.92%
43.42%2.76%2.57%2.60%2.65%2.69%4.12%
83.88%3.18%3.01%2.98%2.99%3.03%4.64%
164.55%3.91%3.69%3.75%3.80%3.77%4.97%

or Create an Account

Close Modal
Close Modal