classifier_scale=30.0 |
classifier_scale=200.0 |
![](https://github.com/KimRass/KimRass/assets/67457712/69992f95-b62c-45be-b583-69cd173e5480) |
![](https://github.com/KimRass/KimRass/assets/67457712/c55cb347-043c-4d41-a66f-f5f6f345c0c5) |
- The classes are "airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "hose", "ship" and "truck" from top to bottom.
3. Theoretical Background
$$x_{t - 1} \leftarrow \text{sample from } \mathcal{N}(\mu + s\Sigma\nabla_{x_{t}}\log{p_{\phi}}(y \vert x), \Sigma)$$
$$\hat{\epsilon} \leftarrow \epsilon_{\theta}(x_{t}) - \sqrt{1 - \bar{\alpha}{t}}\nabla{x_{t}}\log{p_{\phi}}(y \vert x)$$
$$x_{t - 1} \leftarrow \sqrt{\bar{\alpha}{t - 1}}\Bigg(\frac{x{t} - \sqrt{1 - \bar{\alpha}{t}}\hat{\epsilon}}{\sqrt{\bar{\alpha}{t}}}\Bigg) + \sqrt{1 - \bar{\alpha}_{t - 1}}\hat{\epsilon}$$