The encoding vector of a Conditional Variational Autoencoder (CVAE) is comprised of two components - the style encoding, and the conditioning vector. This visualization explores how each of these affects the generative output of the decoder model. Drag the point in the 2D chart to modify the style, and use the sliders to modify the condits.
| 0 | ||
| 1 | ||
| 2 | ||
| 3 | ||
| 4 | 5 | |
| 6 | ||
| 7 | ||
| 8 | ||
| 9 | ||