Skip to content

Commit 6347a7d

Browse files
authored
Update README.md
add news and link to latent diffusion.
1 parent 29b803f commit 6347a7d

File tree

1 file changed

+6
-0
lines changed

1 file changed

+6
-0
lines changed

README.md

+6
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,10 @@
1515

1616

1717
### 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
1822
- Thanks to [rom1504](https://github.com/rom1504) it is now easy to [train a VQGAN on your own datasets](#training-on-custom-data).
1923
- Included a bugfix for the quantizer. For backward compatibility it is
2024
disabled by default (which corresponds to always training with `beta=1.0`).
@@ -63,6 +67,8 @@ for a comparison and discussion of reconstruction capabilities.
6367
| | | | | || |
6468
| VQGAN ImageNet (f=16), 1024 | 10.54 | 7.94 | [vqgan_imagenet_f16_1024](https://heibox.uni-heidelberg.de/d/8088892a516d4e3baf92/) | [reconstructions](https://k00.fr/j626x093) | Reconstruction-FIDs.
6569
| VQGAN ImageNet (f=16), 16384 | 7.41 | 4.98 |[vqgan_imagenet_f16_16384](https://heibox.uni-heidelberg.de/d/a7530b09fed84f80a887/) | [reconstructions](https://k00.fr/j626x093) | Reconstruction-FIDs.
70+
| VQGAN OpenImages (f=8), 256 | -- | 1.49 |https://ommer-lab.com/files/latent-diffusion/vq-f8-n256.zip | --- | Reconstruction-FIDs. Available via [latent diffusion](https://github.com/CompVis/latent-diffusion).
71+
| VQGAN OpenImages (f=8), 16384 | -- | 1.14 |https://ommer-lab.com/files/latent-diffusion/vq-f8.zip | --- | Reconstruction-FIDs. Available via [latent diffusion](https://github.com/CompVis/latent-diffusion)
6672
| VQGAN OpenImages (f=8), 8192, GumbelQuantization | 3.24 | 1.49 |[vqgan_gumbel_f8](https://heibox.uni-heidelberg.de/d/2e5662443a6b4307b470/) | --- | Reconstruction-FIDs.
6773
| | | | | || |
6874
| DALL-E dVAE (f=8), 8192, GumbelQuantization | 33.88 | 32.01 | https://github.com/openai/DALL-E | [reconstructions](https://k00.fr/j626x093) | Reconstruction-FIDs.

0 commit comments

Comments
 (0)