Spaces:
Running
on
Zero
Running
on
Zero
zejunyang
commited on
Commit
•
1be0964
1
Parent(s):
27146ed
init
Browse files- pretrained_model/sd-vae-ft-mse +0 -1
- pretrained_model/sd-vae-ft-mse/.gitattributes +33 -0
- pretrained_model/sd-vae-ft-mse/README.md +83 -0
- pretrained_model/sd-vae-ft-mse/config.json +29 -0
- pretrained_model/sd-vae-ft-mse/diffusion_pytorch_model.bin +3 -0
- pretrained_model/sd-vae-ft-mse/diffusion_pytorch_model.safetensors +3 -0
pretrained_model/sd-vae-ft-mse
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
Subproject commit 31f26fdeee1355a5c34592e401dd41e45d25a493
|
|
|
|
pretrained_model/sd-vae-ft-mse/.gitattributes
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
24 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
33 |
+
diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
|
pretrained_model/sd-vae-ft-mse/README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- stable-diffusion
|
5 |
+
- stable-diffusion-diffusers
|
6 |
+
inference: false
|
7 |
+
---
|
8 |
+
# Improved Autoencoders
|
9 |
+
|
10 |
+
## Utilizing
|
11 |
+
These weights are intended to be used with the [🧨 diffusers library](https://github.com/huggingface/diffusers). If you are looking for the model to use with the original [CompVis Stable Diffusion codebase](https://github.com/CompVis/stable-diffusion), [come here](https://huggingface.co/stabilityai/sd-vae-ft-mse-original).
|
12 |
+
|
13 |
+
#### How to use with 🧨 diffusers
|
14 |
+
You can integrate this fine-tuned VAE decoder to your existing `diffusers` workflows, by including a `vae` argument to the `StableDiffusionPipeline`
|
15 |
+
```py
|
16 |
+
from diffusers.models import AutoencoderKL
|
17 |
+
from diffusers import StableDiffusionPipeline
|
18 |
+
|
19 |
+
model = "CompVis/stable-diffusion-v1-4"
|
20 |
+
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")
|
21 |
+
pipe = StableDiffusionPipeline.from_pretrained(model, vae=vae)
|
22 |
+
```
|
23 |
+
|
24 |
+
## Decoder Finetuning
|
25 |
+
We publish two kl-f8 autoencoder versions, finetuned from the original [kl-f8 autoencoder](https://github.com/CompVis/latent-diffusion#pretrained-autoencoding-models) on a 1:1 ratio of [LAION-Aesthetics](https://laion.ai/blog/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.
|
26 |
+
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).
|
27 |
+
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
|
28 |
+
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).
|
29 |
+
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.
|
30 |
+
|
31 |
+
_Original kl-f8 VAE vs f8-ft-EMA vs f8-ft-MSE_
|
32 |
+
|
33 |
+
## Evaluation
|
34 |
+
### COCO 2017 (256x256, val, 5000 images)
|
35 |
+
| Model | train steps | rFID | PSNR | SSIM | PSIM | Link | Comments
|
36 |
+
|----------|---------|------|--------------|---------------|---------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
|
37 |
+
| | | | | | | | |
|
38 |
+
| 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 |
|
39 |
+
| 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 |
|
40 |
+
| 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 |
|
41 |
+
|
42 |
+
|
43 |
+
### LAION-Aesthetics 5+ (256x256, subset, 10000 images)
|
44 |
+
| Model | train steps | rFID | PSNR | SSIM | PSIM | Link | Comments
|
45 |
+
|----------|-----------|------|--------------|---------------|---------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
|
46 |
+
| | | | | | | | |
|
47 |
+
| 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 |
|
48 |
+
| 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 |
|
49 |
+
| 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 |
|
50 |
+
|
51 |
+
|
52 |
+
### Visual
|
53 |
+
_Visualization of reconstructions on 256x256 images from the COCO2017 validation dataset._
|
54 |
+
|
55 |
+
<p align="center">
|
56 |
+
<br>
|
57 |
+
<b>
|
58 |
+
256x256: ft-EMA (left), ft-MSE (middle), original (right)</b>
|
59 |
+
</p>
|
60 |
+
|
61 |
+
<p align="center">
|
62 |
+
<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00025_merged.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/merged/00011_merged.png />
|
67 |
+
</p>
|
68 |
+
|
69 |
+
<p align="center">
|
70 |
+
<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00037_merged.png />
|
71 |
+
</p>
|
72 |
+
|
73 |
+
<p align="center">
|
74 |
+
<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00043_merged.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/merged/00053_merged.png />
|
79 |
+
</p>
|
80 |
+
|
81 |
+
<p align="center">
|
82 |
+
<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00029_merged.png />
|
83 |
+
</p>
|
pretrained_model/sd-vae-ft-mse/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.4.2",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"block_out_channels": [
|
6 |
+
128,
|
7 |
+
256,
|
8 |
+
512,
|
9 |
+
512
|
10 |
+
],
|
11 |
+
"down_block_types": [
|
12 |
+
"DownEncoderBlock2D",
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D"
|
16 |
+
],
|
17 |
+
"in_channels": 3,
|
18 |
+
"latent_channels": 4,
|
19 |
+
"layers_per_block": 2,
|
20 |
+
"norm_num_groups": 32,
|
21 |
+
"out_channels": 3,
|
22 |
+
"sample_size": 256,
|
23 |
+
"up_block_types": [
|
24 |
+
"UpDecoderBlock2D",
|
25 |
+
"UpDecoderBlock2D",
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D"
|
28 |
+
]
|
29 |
+
}
|
pretrained_model/sd-vae-ft-mse/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
|
3 |
+
size 334707217
|
pretrained_model/sd-vae-ft-mse/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
|
3 |
+
size 334643276
|