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
Copy file name to clipboardExpand all lines: README.md
+6
Original file line number
Diff line number
Diff line change
@@ -15,6 +15,10 @@
15
15
16
16
17
17
### News
18
+
#### 2022
19
+
- More pretrained VQGANs (e.g. a f8-model with only 256 codebook entries) are available in our new work on [Latent Diffusion Models](https://github.com/CompVis/latent-diffusion).
20
+
- Added scene synthesis models as proposed in the paper [High-Resolution Complex Scene Synthesis with Transformers](https://arxiv.org/abs/2105.06458), see [this section](#scene-image-synthesis).
21
+
#### 2021
18
22
- Thanks to [rom1504](https://github.com/rom1504) it is now easy to [train a VQGAN on your own datasets](#training-on-custom-data).
19
23
- Included a bugfix for the quantizer. For backward compatibility it is
20
24
disabled by default (which corresponds to always training with `beta=1.0`).
@@ -63,6 +67,8 @@ for a comparison and discussion of reconstruction capabilities.
0 commit comments