You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
A labelled dataset of cat and dog photos (source, Pexels.com).
182
-
</figcaption>
183
-
</figure>
113
+
<TypicalGallerydata={catDogGallery}caption="A labelled dataset of cat and dog photos (source, Pexels.com)." />
114
+
184
115
185
116
186
117
**Assumption** For *class-conditional* generative models, the assumption is that the data $x_1, \dots, x_n$, is drawn from some *unknown* underlying conditional probability distribution**s** $p_{data}( \cdot | y = y_i)$: for all $i \in 1, \dots, n$
A dataset of cat and dog photos, and their text description (source, Pexels.com).
277
-
</figcaption>
278
-
</figure>
174
+
<TypicalGallerydata={catDogTextGallery}caption="A dataset of cat and dog photos, and their text description (source, Pexels.com)." />
279
175
280
176
281
177
For instance, [Stable Diffusion](https://stabledifffusion.com/) was trained on the [LAION-5B dataset](https://laion.ai/blog/laion-5b/), a dataset of 5 billion images and their textual description.
0 commit comments