Hugging Face's logo

stabilityai
/
sd-vae-ft-ema-original

Text-to-Image
stable-diffusion
stable-diffusion-diffusers
Model card Files Community
3
multimodalart HF staff commited on
Commit
fda49c0
•
1 Parent(s): b7e7887

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -19
README.md CHANGED
@@ -1,3 +1,11 @@
 
 
 
 
 
 
 
 
1
  # Improved Autoencoders
2
  ## Decoder Finetuning
3
  We publish two kl-f8 autoencoder versions, finetuned from the original [kl-f8 autoencoder](https://github.com/CompVis/latent-diffusion#pretrained-autoencoding-models).
@@ -33,41 +41,41 @@ _Visualization of reconstructions on 256x256 images from the COCO2017 validatio
33
  <p align="center">
34
  <br>
35
  <b>
36
- 256x256: ft-MSE (left), ft-EMA (middle), original (right)</b>
37
  </p>
38
 
39
  <p align="center">
40
- <img src=eval/ae-decoder-tuning-reconstructions/ft-mse/00025.png />
41
- <img src=eval/ae-decoder-tuning-reconstructions/ft-ema/00025.png />
42
- <img src=eval/ae-decoder-tuning-reconstructions/original/00025.png />
43
  </p>
44
 
45
  <p align="center">
46
- <img src=eval/ae-decoder-tuning-reconstructions/ft-mse/00011.png />
47
- <img src=eval/ae-decoder-tuning-reconstructions/ft-ema/00011.png />
48
- <img src=eval/ae-decoder-tuning-reconstructions/original/00011.png />
49
  </p>
50
 
51
  <p align="center">
52
- <img src=eval/ae-decoder-tuning-reconstructions/ft-mse/00037.png />
53
- <img src=eval/ae-decoder-tuning-reconstructions/ft-ema/00037.png />
54
- <img src=eval/ae-decoder-tuning-reconstructions/original/00037.png />
55
  </p>
56
 
57
  <p align="center">
58
- <img src=eval/ae-decoder-tuning-reconstructions/ft-mse/00043.png />
59
- <img src=eval/ae-decoder-tuning-reconstructions/ft-ema/00043.png />
60
- <img src=eval/ae-decoder-tuning-reconstructions/original/00043.png />
61
  </p>
62
 
63
  <p align="center">
64
- <img src=eval/ae-decoder-tuning-reconstructions/ft-mse/00053.png />
65
- <img src=eval/ae-decoder-tuning-reconstructions/ft-ema/00053.png />
66
- <img src=eval/ae-decoder-tuning-reconstructions/original/00053.png />
67
  </p>
68
 
69
  <p align="center">
70
- <img src=eval/ae-decoder-tuning-reconstructions/ft-mse/00029.png />
71
- <img src=eval/ae-decoder-tuning-reconstructions/ft-ema/00029.png />
72
- <img src=eval/ae-decoder-tuning-reconstructions/original/00029.png />
73
  </p>
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ tags:
4
+ - stable-diffusion
5
+ - stable-diffusion-diffusers
6
+ - text-to-image
7
+ inference: false
8
+ ---
9
  # Improved Autoencoders
10
  ## Decoder Finetuning
11
  We publish two kl-f8 autoencoder versions, finetuned from the original [kl-f8 autoencoder](https://github.com/CompVis/latent-diffusion#pretrained-autoencoding-models).
 
41
  <p align="center">
42
  <br>
43
  <b>
44
+ 256x256: ft-MSE (top), ft-EMA (middle), original (right)</b>
45
  </p>
46
 
47
  <p align="center">
48
+ <img src="https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-mse/00025.png" />
49
+ <img src="https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-ema/00025.png" />
50
+ <img src="https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/original/00025.png" />
51
  </p>
52
 
53
  <p align="center">
54
+ <img src="https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-mse/00011.png" />
55
+ <img src="https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-ema/00011.png" />
56
+ <img src="https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/original/00011.png" />
57
  </p>
58
 
59
  <p align="center">
60
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-mse/00037.png />
61
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-ema/00037.png />
62
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/original/00037.png />
63
  </p>
64
 
65
  <p align="center">
66
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-mse/00043.png />
67
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-ema/00043.png />
68
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/original/00043.png />
69
  </p>
70
 
71
  <p align="center">
72
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-mse/00053.png />
73
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-ema/00053.png />
74
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/original/00053.png />
75
  </p>
76
 
77
  <p align="center">
78
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-mse/00029.png />
79
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/ft-ema/00029.png />
80
+ <img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/original/00029.png />
81
  </p>