You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<p style="padding: 0; margin: 0;"><b>Disclaimer: </b>This software is still in beta, bugs can and will occur at some point. Please use the <i>Issues</i> tab to report a bug. Thank you for using SDToolkit!</p>
7
+
</div>
8
+
<br/>
9
+
10
+

11
+

12
+
13
+
## Features
14
+
15
+
- No setup required, just install and run
16
+
- Video2x upscaler
17
+
- GFPGAN face restoration
18
+
- Ability to choose a context image for AI to try to match
19
+
- Result image viewer with zoom
20
+
- Optimized for low VRAM GPUs
21
+
- Many helpful tooltips that make it very easy to use
22
+
- Decent amount of configuration options
23
+
24
+
## GFPGAN Integration
25
+
26
+
SDToolkit offers a built-in GFPGAN for face restoration. This is quite a powerful tool to remove face artifacts and beautify the result. It's definitely recommended to use GFPGAN for every prompt that might have faces in it.
27
+
28
+

29
+
30
+
## Video2x Upscaler
31
+
32
+
SDToolkit offers a built-in Video2x upscaler. Please remember that it isn't perfect, and upscaling by a very large factor can cause artifacts.
33
+
34
+

7
35
8
36
## Requirements / Info
9
37
10
38
- OS: Windows 64-bit
11
-
- At least 25GB of disk space
39
+
- At least 35GB of disk space
12
40
- At least 8GB of GPU VRAM is recommended
13
41
- At least 16GB of RAM is recommended
14
42
- CUDA-enabled GPU is recommended (Nvidia)
15
43
16
-
Since SDToolkit is all-in-one software, the model, upscaling software (video2x) and execution environment (Conda/Python) is included in the setup.
44
+
Since SDToolkit is all-in-one software, the model, upscaling software (video2x/GFPGAN) and execution environment (Conda/Python) is included in the setup.
17
45
18
46
Tested with i7-12700KF and GTX 1080 with full precision. (around 6.7GB of VRAM usage)
19
47
20
48
Half precision is recommended for RTX cards.
21
49
22
50
## Installation
23
51
24
-
Just download and run the setup from the Releases tab. Be reminded that it's a huge file, you should have at least 20-25GB of free disk space.
52
+
Just download and run the setup from the Releases tab. Be reminded that it's a huge file, you should have at least 35GB of free disk space.
25
53
26
54
## License
27
55
@@ -35,3 +63,5 @@ You're free to download it yourself at [CompVis's huggingface repository](https:
35
63
Scripts and model execution software provided by [basujindal's fork of stable diffusion](https://github.com/basujindal/stable-diffusion/).
36
64
37
65
Upscaling model and algorithm is provided by [video2x](https://github.com/k4yt3x/video2x).
66
+
67
+
GFPGAN 1.3 model and algorithm provided by [Tencent's GFPGAN](https://github.com/TencentARC/GFPGAN).
0 commit comments