Total runs:
154.9K
Run Growth:
82.6K
Growth Rate:
53.25%
Sponsored by
NewsBang
diffusers / sd-vae-ft-mse
Model's Last Updated: February 24 2025
Introduction of sd-vae-ft-mse
Model Details of sd-vae-ft-mse
Improved Autoencoders
Utilizing
These weights are intended to be used with the 🧨 diffusers library . If you are looking for the model to use with the original CompVis Stable Diffusion codebase , come here .
How to use with 🧨 diffusers
You can integrate this fine-tuned VAE decoder to your existing
diffusers
workflows, by including a
vae
argument to the
StableDiffusionPipeline
from diffusers.models import AutoencoderKL
from diffusers import StableDiffusionPipeline
model = "CompVis/stable-diffusion-v1-4"
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")
pipe = StableDiffusionPipeline.from_pretrained(model, vae=vae)
Decoder Finetuning
We publish two kl-f8 autoencoder versions, finetuned from the original kl-f8 autoencoder on a 1:1 ratio of LAION-Aesthetics and LAION-Humans, an unreleased subset containing only SFW images of humans. The intent was to fine-tune on the Stable Diffusion training set (the autoencoder was originally trained on OpenImages) but also enrich the dataset with images of humans to improve the reconstruction of faces. The first, ft-EMA , was resumed from the original checkpoint, trained for 313198 steps and uses EMA weights. It uses the same loss configuration as the original checkpoint (L1 + LPIPS). The second, ft-MSE , was resumed from ft-EMA and uses EMA weights and was trained for another 280k steps using a different loss, with more emphasis on MSE reconstruction (MSE + 0.1 * LPIPS). It produces somewhat ``smoother'' outputs. The batch size for both versions was 192 (16 A100s, batch size 12 per GPU). To keep compatibility with existing models, only the decoder part was finetuned; the checkpoints can be used as a drop-in replacement for the existing autoencoder.
Original kl-f8 VAE vs f8-ft-EMA vs f8-ft-MSE
Evaluation
COCO 2017 (256x256, val, 5000 images)
| Model | train steps | rFID | PSNR | SSIM | PSIM | Link | Comments |
|---|---|---|---|---|---|---|---|
| original | 246803 | 4.99 | 23.4 +/- 3.8 | 0.69 +/- 0.14 | 1.01 +/- 0.28 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip | as used in SD |
| ft-EMA | 560001 | 4.42 | 23.8 +/- 3.9 | 0.69 +/- 0.13 | 0.96 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt | slightly better overall, with EMA |
| ft-MSE | 840001 | 4.70 | 24.5 +/- 3.7 | 0.71 +/- 0.13 | 0.92 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
LAION-Aesthetics 5+ (256x256, subset, 10000 images)
| Model | train steps | rFID | PSNR | SSIM | PSIM | Link | Comments |
|---|---|---|---|---|---|---|---|
| original | 246803 | 2.61 | 26.0 +/- 4.4 | 0.81 +/- 0.12 | 0.75 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip | as used in SD |
| ft-EMA | 560001 | 1.77 | 26.7 +/- 4.8 | 0.82 +/- 0.12 | 0.67 +/- 0.34 | https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt | slightly better overall, with EMA |
| ft-MSE | 840001 | 1.88 | 27.3 +/- 4.7 | 0.83 +/- 0.11 | 0.65 +/- 0.34 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
Visual
Visualization of reconstructions on 256x256 images from the COCO2017 validation dataset.
256x256: ft-EMA (left), ft-MSE (middle), original (right)
Runs of diffusers sd-vae-ft-mse on huggingface.co
30
Total runs
0
24-hour runs
7
3-day runs
-5
7-day runs
-5
30-day runs
More Information About sd-vae-ft-mse huggingface.co Model
Url of sd-vae-ft-mse
sd-vae-ft-mse huggingface.co Url
Provider of sd-vae-ft-mse huggingface.co
Other API from diffusers
Updated:September 04 2023
Total runs:
27.0K
Run Growth:
1.7K
Growth Rate:
6.25%
Total runs:
21.1K
Run Growth:
-8.1K
Growth Rate:
-38.69%
Total runs:
19.3K
Run Growth:
-1.1K
Growth Rate:
-5.95%
Total runs:
8.3K
Run Growth:
1.1K
Growth Rate:
13.13%
Total runs:
4.3K
Run Growth:
3.8K
Growth Rate:
89.24%
Total runs:
3.5K
Run Growth:
507
Growth Rate:
14.32%
Total runs:
3.0K
Run Growth:
381
Growth Rate:
12.68%
Total runs:
1.8K
Run Growth:
43
Growth Rate:
2.36%
Total runs:
1.3K
Run Growth:
750
Growth Rate:
58.32%
Total runs:
1.1K
Run Growth:
-297
Growth Rate:
-27.15%
Total runs:
1.0K
Run Growth:
270
Growth Rate:
26.60%
Total runs:
828
Run Growth:
366
Growth Rate:
44.20%
Total runs:
823
Run Growth:
423
Growth Rate:
51.40%
Total runs:
626
Run Growth:
276
Growth Rate:
44.09%
Total runs:
223
Run Growth:
135
Growth Rate:
60.54%
Total runs:
152
Run Growth:
50
Growth Rate:
32.89%
Total runs:
117
Run Growth:
-20
Growth Rate:
-17.09%
Total runs:
115
Run Growth:
91
Growth Rate:
79.13%
Total runs:
93
Run Growth:
56
Growth Rate:
60.22%
Total runs:
84
Run Growth:
-91
Growth Rate:
-104.60%
Total runs:
61
Run Growth:
58
Growth Rate:
95.08%
Total runs:
20
Run Growth:
3
Growth Rate:
15.00%
Total runs:
20
Run Growth:
-9
Growth Rate:
-39.13%
Total runs:
20
Run Growth:
15
Growth Rate:
75.00%
Total runs:
14
Run Growth:
14
Growth Rate:
100.00%
Total runs:
11
Run Growth:
11
Growth Rate:
100.00%
Total runs:
11
Run Growth:
0
Growth Rate:
0.00%
Total runs:
9
Run Growth:
5
Growth Rate:
55.56%
Total runs:
8
Run Growth:
-4
Growth Rate:
-50.00%
Total runs:
7
Run Growth:
-9
Growth Rate:
-128.57%
Total runs:
6
Run Growth:
-13
Growth Rate:
-216.67%
Total runs:
6
Run Growth:
3
Growth Rate:
50.00%
Total runs:
5
Run Growth:
3
Growth Rate:
60.00%
Total runs:
4
Run Growth:
-3
Growth Rate:
-75.00%
Total runs:
4
Run Growth:
4
Growth Rate:
100.00%
Total runs:
4
Run Growth:
0
Growth Rate:
0.00%
Total runs:
4
Run Growth:
2
Growth Rate:
50.00%
Total runs:
4
Run Growth:
4
Growth Rate:
100.00%
Total runs:
4
Run Growth:
4
Growth Rate:
100.00%
Total runs:
3
Run Growth:
0
Growth Rate:
0.00%
Total runs:
3
Run Growth:
2
Growth Rate:
66.67%
Total runs:
2
Run Growth:
2
Growth Rate:
100.00%
Total runs:
2
Run Growth:
-1
Growth Rate:
-50.00%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1
Run Growth:
-8
Growth Rate:
-800.00%
Total runs:
1
Run Growth:
1
Growth Rate:
100.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%