Skip to content

Commit 417d5f3

Browse files
author
ablattmann
committed
add trainsteps to first stage table
1 parent 8517435 commit 417d5f3

File tree

1 file changed

+14
-13
lines changed

1 file changed

+14
-13
lines changed

‎README.md‎

Lines changed: 14 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -33,19 +33,20 @@ conda activate ldm
3333
## Pretrained Autoencoding Models
3434
![rec2](assets/reconstruction2.png)
3535

36-
37-
| Model | FID vs val | PSNR | PSIM | Link | Comments
38-
|-------------------------|------------|----------------|---------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------|
39-
| f=4, VQ (Z=8192, d=3) | 0.58 | 27.43 +/- 4.26 | 0.53 +/- 0.21 | https://ommer-lab.com/files/latent-diffusion/vq-f4.zip | |
40-
| f=4, VQ (Z=8192, d=3) | 1.06 | 25.21 +/- 4.17 | 0.72 +/- 0.26 | https://heibox.uni-heidelberg.de/f/9c6681f64bb94338a069/?dl=1 | no attention |
41-
| f=8, VQ (Z=16384, d=4) | 1.14 | 23.07 +/- 3.99 | 1.17 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/vq-f8.zip | |
42-
| f=8, VQ (Z=256, d=4) | 1.49 | 22.35 +/- 3.81 | 1.26 +/- 0.37 | https://ommer-lab.com/files/latent-diffusion/vq-f8-n256.zip |
43-
| f=16, VQ (Z=16384, d=8) | 5.15 | 20.83 +/- 3.61 | 1.73 +/- 0.43 | https://heibox.uni-heidelberg.de/f/0e42b04e2e904890a9b6/?dl=1 | |
44-
| | | | | | |
45-
| f=4, KL | 0.27 | 27.53 +/- 4.54 | 0.55 +/- 0.24 | https://ommer-lab.com/files/latent-diffusion/kl-f4.zip | |
46-
| f=8, KL | 0.90 | 24.19 +/- 4.19 | 1.02 +/- 0.35 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip | |
47-
| f=16, KL (d=16) | 0.87 | 24.08 +/- 4.22 | 1.07 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/kl-f16.zip | |
48-
| f=32, KL (d=64) | 2.04 | 22.27 +/- 3.93 | 1.41 +/- 0.40 | https://ommer-lab.com/files/latent-diffusion/kl-f32.zip | |
36+
All models were trained until convergence (no further substantial improvement in rFID).
37+
38+
| Model | rFID vs val | train steps |PSNR | PSIM | Link | Comments
39+
|-------------------------|------------|----------------|----------------|---------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------|
40+
| f=4, VQ (Z=8192, d=3) | 0.58 | 533066 | 27.43 +/- 4.26 | 0.53 +/- 0.21 | https://ommer-lab.com/files/latent-diffusion/vq-f4.zip | |
41+
| f=4, VQ (Z=8192, d=3) | 1.06 | 658131 | 25.21 +/- 4.17 | 0.72 +/- 0.26 | https://heibox.uni-heidelberg.de/f/9c6681f64bb94338a069/?dl=1 | no attention |
42+
| f=8, VQ (Z=16384, d=4) | 1.14 | 971043 | 23.07 +/- 3.99 | 1.17 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/vq-f8.zip | |
43+
| f=8, VQ (Z=256, d=4) | 1.49 | 1608649 | 22.35 +/- 3.81 | 1.26 +/- 0.37 | https://ommer-lab.com/files/latent-diffusion/vq-f8-n256.zip |
44+
| f=16, VQ (Z=16384, d=8) | 5.15 | 1101166 | 20.83 +/- 3.61 | 1.73 +/- 0.43 | https://heibox.uni-heidelberg.de/f/0e42b04e2e904890a9b6/?dl=1 | |
45+
| | | | | | | |
46+
| f=4, KL | 0.27 | 176991 | 27.53 +/- 4.54 | 0.55 +/- 0.24 | https://ommer-lab.com/files/latent-diffusion/kl-f4.zip | |
47+
| f=8, KL | 0.90 | 246803 | 24.19 +/- 4.19 | 1.02 +/- 0.35 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip | |
48+
| f=16, KL (d=16) | 0.87 | 442998 | 24.08 +/- 4.22 | 1.07 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/kl-f16.zip | |
49+
| f=32, KL (d=64) | 2.04 | 406763 | 22.27 +/- 3.93 | 1.41 +/- 0.40 | https://ommer-lab.com/files/latent-diffusion/kl-f32.zip | |
4950

5051
### Get the models
5152

0 commit comments

Comments
 (0)