mirror of
https://github.com/vladmandic/automatic
synced 2026-09-20 01:31:13 +02:00
update wiki links
Signed-off-by: Vladimir Mandic <mandic00@live.com>
Vladimir Mandic
+2
-2
@@ -84,7 +84,7 @@ This guide is for users with AMD GPUs lacking official ROCm/[HIP SDK](https://ww
|
||||
If you already have the libraries, you can skip this section!
|
||||
|
||||
To build your own rocBLAS, follow this guide. A simplified version is available on GitHub:
|
||||
[ROCm-HIP-SDK-Windows-Support](https://github.com/vladmandic/automatic/wiki/ROCm-HIP-SDK-Windows-Support).
|
||||
[ROCm-HIP-SDK-Windows-Support](https://github.com/vladmandic/sdnext/wiki/ROCm-HIP-SDK-Windows-Support).
|
||||
|
||||
**Prerequisites:** Ensure the following software is installed on your PC. `python`, `git`, and the `HIP SDK`are
|
||||
essential. The script `rdeps.py` will automatically download any missing dependencies when you run it.
|
||||
@@ -115,7 +115,7 @@ essential. The script `rdeps.py` will automatically download any missing depend
|
||||
## Patching Tensile for ROCm (For Advanced Users, Not-a-must-Do)
|
||||
|
||||
These steps are necessary for specific configurations of ROCm and may not be required in all cases.
|
||||
If you had a optimized logic for you gpu arche or [do the necessary edit as guide here](https://github.com/vladmandic/automatic/wiki/Rocm-Support#note-editing-tensilecommonpy),you may skip this steps.Especily build libs for xnack- features.
|
||||
If you had a optimized logic for you gpu arche or [do the necessary edit as guide here](https://github.com/vladmandic/sdnext/wiki/Rocm-Support#note-editing-tensilecommonpy),you may skip this steps.Especily build libs for xnack- features.
|
||||
|
||||
### Determine Your ROCm Version:
|
||||
|
||||
|
||||
+6
-6
@@ -103,7 +103,7 @@ Basic tests using UI:
|
||||
```log
|
||||
2024-02-07 22:52:56,406 INFO: {'run-benchmark'}
|
||||
2024-02-07 22:52:56,407 INFO: {'options': {'prompt': 'photo of two dice on a table', 'negative_prompt': 'foggy, blurry', 'steps': 50, 'sampler_name': 'Euler a', 'width': 512, 'height': 512, 'full_quality': True, 'cfg_scale': 0, 'batch_size': 1, 'n_iter': 1, 'seed': -1}}
|
||||
2024-02-07 22:52:56,432 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/automatic/tree/dev'}}
|
||||
2024-02-07 22:52:56,432 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/sdnext/tree/dev'}}
|
||||
2024-02-07 22:52:56,434 INFO: {'platform': {'arch': 'x86_64', 'cpu': '', 'system': 'Linux', 'release': '6.7.3-arch1-2', 'python': '3.11.6', 'torch': '2.1.0a0+cxx11.abi', 'diffusers': '0.26.2', 'gradio': '3.43.2'}}
|
||||
2024-02-07 22:52:56,437 INFO: {'model': 'SD1.5/SoteMixV3 [dcc16969a0]'}
|
||||
2024-02-07 22:52:56,441 INFO: {'system': {'cpu': {'free': 48901079040.00001, 'used': 1533939712, 'total': 50435018752.00001}, 'gpu': {'system': {'free': 17079205888, 'used': 0, 'total': 17079205888}, 'session': {'current': 0, 'peak': 0}}}}
|
||||
@@ -162,7 +162,7 @@ Possible max batch size: 12 (Slow with 12, OOM with 16)
|
||||
```log
|
||||
2024-02-08 20:09:31,923 INFO: {'run-benchmark'}
|
||||
2024-02-08 20:09:31,924 INFO: {'options': {'prompt': 'photo of two dice on a table', 'negative_prompt': 'foggy, blurry', 'steps': 50, 'sampler_name': 'Euler a', 'width': 512, 'height': 512, 'full_quality': True, 'cfg_scale': 0, 'batch_size': 1, 'n_iter': 1, 'seed': -1}}
|
||||
2024-02-08 20:09:32,005 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/automatic/tree/dev'}}
|
||||
2024-02-08 20:09:32,005 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/sdnext/tree/dev'}}
|
||||
2024-02-08 20:09:32,007 INFO: {'platform': {'arch': 'AMD64', 'cpu': 'Intel64 Family 6 Model 183 Stepping 1, GenuineIntel', 'system': 'Windows', 'release': 'Windows-10-10.0.22631-SP0', 'python': '3.10.11', 'torch': '2.0.0+cpu', 'diffusers': '0.26.2', 'gradio': '3.43.2'}}
|
||||
2024-02-08 20:09:32,013 INFO: {'system': {'cpu': {'free': 136382431232.00002, 'used': 708612096, 'total': 137091043328.00002}, 'gpu': {'error': 'unavailable'}}}
|
||||
2024-02-08 20:09:32,013 INFO: {'batch-sizes': [1, 1, 2, 4, 8, 12, 16]}
|
||||
@@ -191,7 +191,7 @@ Possible max batch size: 8 (Not OOM, but very slow with 12 or higher)
|
||||
```log
|
||||
2024-02-08 19:20:45,235 INFO: {'run-benchmark'}
|
||||
2024-02-08 19:20:45,236 INFO: {'options': {'prompt': 'photo of two dice on a table', 'negative_prompt': 'foggy, blurry', 'steps': 50, 'sampler_name': 'Euler a', 'width': 512, 'height': 512, 'full_quality': True, 'cfg_scale': 0, 'batch_size': 1, 'n_iter': 1, 'seed': -1}}
|
||||
2024-02-08 19:20:45,317 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/automatic/tree/dev'}}
|
||||
2024-02-08 19:20:45,317 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/sdnext/tree/dev'}}
|
||||
2024-02-08 19:20:45,318 INFO: {'platform': {'arch': 'AMD64', 'cpu': 'Intel64 Family 6 Model 183 Stepping 1, GenuineIntel', 'system': 'Windows', 'release': 'Windows-10-10.0.22631-SP0', 'python': '3.10.12', 'torch': '2.2.0+cpu', 'diffusers': '0.26.2', 'gradio': '3.43.2'}}
|
||||
2024-02-08 19:20:45,324 INFO: {'system': {'cpu': {'free': 136392728576.00002, 'used': 698314752, 'total': 137091043328.00002}, 'gpu': {'error': 'unavailable'}}}
|
||||
2024-02-08 19:20:45,324 INFO: {'batch-sizes': [1, 1, 2, 4, 8, 12, 16]}
|
||||
@@ -215,7 +215,7 @@ Possible max batch size: Unknown (at least 48)
|
||||
```log
|
||||
2024-02-08 18:51:28,096 INFO: {'run-benchmark'}
|
||||
2024-02-08 18:51:28,097 INFO: {'options': {'prompt': 'photo of two dice on a table', 'negative_prompt': 'foggy, blurry', 'steps': 50, 'sampler_name': 'Euler a', 'width': 512, 'height': 512, 'full_quality': True, 'cfg_scale': 0, 'batch_size': 1, 'n_iter': 1, 'seed': -1}}
|
||||
2024-02-08 18:51:28,167 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/automatic/tree/dev'}}
|
||||
2024-02-08 18:51:28,167 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': '659ad2e7', 'url': 'https://github.com/vladmandic/sdnext/tree/dev'}}
|
||||
2024-02-08 18:51:28,168 INFO: {'platform': {'arch': 'AMD64', 'cpu': 'Intel64 Family 6 Model 183 Stepping 1, GenuineIntel', 'system': 'Windows', 'release': 'Windows-10-10.0.22631-SP0', 'python': '3.10.12', 'torch': '2.2.0+cpu', 'diffusers': '0.26.2', 'gradio': '3.43.2'}}
|
||||
2024-02-08 18:51:28,174 INFO: {'system': {'cpu': {'free': 136385822719.99998, 'used': 705220608, 'total': 137091043327.99998}, 'gpu': {'error': 'unavailable'}}}
|
||||
2024-02-08 18:51:28,174 INFO: {'batch-sizes': [1, 1, 2, 4, 8, 12, 16]}
|
||||
@@ -241,7 +241,7 @@ As you can see, we're reaching peak performance of **~110 it/s** using simple se
|
||||
vlado@wsl:~/dev/sdnext-dev $ python cli/run-benchmark.py --maxbatch 32
|
||||
2024-02-07 11:19:53,026 INFO: {'run-benchmark'}
|
||||
2024-02-07 11:19:53,027 INFO: {'options': {'prompt': 'photo of two dice on a table', 'negative_prompt': 'foggy, blurry', 'steps': 50, 'sampler_name': 'Euler a', 'width': 512, 'height': 512, 'full_quality': True, 'cfg_scale': 0, 'batch_size': 1, 'n_iter': 1, 'seed': -1}}
|
||||
2024-02-07 11:19:53,046 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': 'd967bd03', 'url': 'https://github.com/vladmandic/automatic/tree/dev'}}
|
||||
2024-02-07 11:19:53,046 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': 'd967bd03', 'url': 'https://github.com/vladmandic/sdnext/tree/dev'}}
|
||||
2024-02-07 11:19:53,048 INFO: {'platform': {'arch': 'x86_64', 'cpu': 'x86_64', 'system': 'Linux', 'release': '5.15.146.1-microsoft-standard-WSL2', 'python': '3.11.1', 'torch': '2.2.0+cu121', 'diffusers': '0.26.2', 'gradio': '3.43.2'}}
|
||||
2024-02-07 11:19:53,051 INFO: {'model': 'sd15/lyriel-v16 [ec6f68ea63]'}
|
||||
2024-02-07 11:19:53,054 INFO: {'system': {'cpu': {'free': 49020043264.0, 'used': 1495736320, 'total': 50515779584.0}, 'gpu': {'system': {'free': 24110956544, 'used': 1645740032, 'total': 25756696576}, 'session': {'current': 0, 'peak': 0}}}}
|
||||
@@ -264,7 +264,7 @@ We're reaching peak performance of **~150 it/s** (and **~165 it/s** using *TAESD
|
||||
vlado@wsl:~/dev/sdnext-dev $ python cli/run-benchmark.py --maxbatch 32
|
||||
2024-02-07 11:29:23,431 INFO: {'run-benchmark'}
|
||||
2024-02-07 11:29:23,432 INFO: {'options': {'prompt': 'photo of two dice on a table', 'negative_prompt': 'foggy, blurry', 'steps': 50, 'sampler_name': 'Euler a', 'width': 512, 'height': 512, 'full_quality': True, 'cfg_scale': 0, 'batch_size': 1, 'n_iter': 1, 'seed': -1}}
|
||||
2024-02-07 11:29:23,451 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': 'd967bd03', 'url': 'https://github.com/vladmandic/automatic/tree/dev'}}
|
||||
2024-02-07 11:29:23,451 INFO: {'version': {'app': 'sd.next', 'updated': '2024-02-07', 'hash': 'd967bd03', 'url': 'https://github.com/vladmandic/sdnext/tree/dev'}}
|
||||
2024-02-07 11:29:23,453 INFO: {'platform': {'arch': 'x86_64', 'cpu': 'x86_64', 'system': 'Linux', 'release': '5.15.146.1-microsoft-standard-WSL2', 'python': '3.11.1', 'torch': '2.2.0+cu121', 'diffusers': '0.26.2', 'gradio': '3.43.2'}}
|
||||
2024-02-07 11:29:23,456 INFO: {'model': 'sd15/lyriel-v16 [ec6f68ea63]'}
|
||||
2024-02-07 11:29:23,459 INFO: {'system': {'cpu': {'free': 49373564927.99999, 'used': 1142214656, 'total': 50515779583.99999}, 'gpu': {'system': {'free': 24110956544, 'used': 1645740032, 'total': 25756696576}, 'session': {'current': 0, 'peak': 0}}}}
|
||||
|
||||
+1
-1
@@ -142,7 +142,7 @@
|
||||
|
||||
### Troubleshooting Options
|
||||
|
||||
**Also see [Troubleshooting Wiki page](https://github.com/vladmandic/automatic/wiki/Troubleshooting)**
|
||||
**Also see [Troubleshooting Wiki page](https://github.com/vladmandic/sdnext/wiki/Troubleshooting)**
|
||||
|
||||
- `--safe`: Run in safe mode with no user extensions. Safe mode can be useful when troubleshooting or when you want to restrict the execution of potentially unsafe user-provided code. Enabling this flag (`True`) runs the application in safe mode, disabling user extensions. The default is `False`, and you can set it to `True` using the environment variable `SD_SAFE`.
|
||||
**Try this first.**
|
||||
|
||||
+9
-9
@@ -12,11 +12,11 @@ This guide will attempt to explain how to use it so that anyone can understand i
|
||||
|
||||
### Input
|
||||
|
||||
The Input control is exactly what it sounds like, it controls what input images (or videos) are contributing to your image generation, by default that is just the image in [Control input pane](https://github.com/vladmandic/automatic/wiki/control-guide#control-input), however if you select `Separate init image`, another image pane will appear below, allowing you to use that as well.
|
||||
The Input control is exactly what it sounds like, it controls what input images (or videos) are contributing to your image generation, by default that is just the image in [Control input pane](https://github.com/vladmandic/sdnext/wiki/control-guide#control-input), however if you select `Separate init image`, another image pane will appear below, allowing you to use that as well.
|
||||
|
||||
**Note:** When using a Control input image as well as a Init input image, the Init input dominates. Adjusting denoise to >=0.9 is recommended, as that will allow the Control input to balance with the Init input. Higher values will increase the strength of Control input further, giving it dominance.
|
||||
|
||||
|
||||
|
||||
|
||||
`Show Preview` is simple, it controls the visibility of the preview window in the far right of the middle row. You'll want this on if you're doing any kind of masking or manipulations that you would want to preview before generating.
|
||||
|
||||
@@ -33,7 +33,7 @@ There are 3 different Input types:
|
||||
This can be a little confusing at first because of the `Before` and `After` subtabs, however it's really quite simple and extremely powerful.
|
||||
The Control size menu allows you to manipulate the size of your input images before and after inference takes place.
|
||||
|
||||
|
||||
|
||||
|
||||
The `Before` subtab does 2 things:
|
||||
|
||||
@@ -51,7 +51,7 @@ The `After` subtab controls any upscaling or downscaling that would take place *
|
||||
|
||||
The Mask controls are where we start getting into the real meat of Control, not only does it allow a plethora of different options to mask, segment, and control the view of your masking with various preview types, but it comes with **22 different colormaps for your viewing pleasure!** (And I think vlad made some of those words up 🤫)
|
||||
|
||||
|
||||
|
||||
|
||||
- `Live update`: With this checked, your masking will update as you make changes to it, if this is off, you will need to hit the `Refresh` button to the right to have your preview pane update, making more changes to it while it is processing may lead to it being desynchronized, just hit the refresh button if it does not look correct.
|
||||
|
||||
@@ -61,7 +61,7 @@ The Mask controls are where we start getting into the real meat of Control, not
|
||||
|
||||
- `Auto-mask`: There are three options here, Threshold, Edge, and Greyscale. Each provides a different method of auto-masking your images.
|
||||
|
||||
- `Auto-segment`: Just like Auto-mask, we have provided an extensive list of [Auto-segmentation models](https://github.com/vladmandic/automatic/wiki/control#segmentation-models), they don't require ControlNet to handle the process, but may take a few seconds to process, depending on your GPU.
|
||||
- `Auto-segment`: Just like Auto-mask, we have provided an extensive list of [Auto-segmentation models](https://github.com/vladmandic/sdnext/wiki/control#segmentation-models), they don't require ControlNet to handle the process, but may take a few seconds to process, depending on your GPU.
|
||||
|
||||
- `Preview`: You can select the preview type here, we have provided 5 modes, Masked, Binary, Greyscale, Color, and Composite, which is the default.
|
||||
|
||||
@@ -79,7 +79,7 @@ The Video controls are quite exciting and fun to play with, with our tools now y
|
||||
With these simple controls, you can tweak your video output with surprising flexibility.
|
||||
Some video output methods provide more controls, try them all.
|
||||
|
||||
|
||||
|
||||
|
||||
- `Skip input frames`: This setting controls how many frames are processed from input instead of every frame. Setting it to 0 would mean processing every frame, a setting of 1 would process every other frame, a setting of 2 would process every third frame, cutting the number of total frames by 2/3rds, and so on.
|
||||
|
||||
@@ -103,13 +103,13 @@ These are some nice goodies that we have cooked up so that no actual installed e
|
||||
|
||||
This is our IP Adapter implementation, with 10 available models for your image or face cloning needs!
|
||||
|
||||
|
||||
|
||||
|
||||
## Image Panes
|
||||
|
||||
You may notice small icons above the image panes that look like pencils, these are Interrogate buttons. The left one is BLIP, and the right one is DeepBooru. Click one of the buttons to interrogate the image in the pane below it. The results will appear in your prompt area.
|
||||
|
||||
|
||||
|
||||
|
||||
### Control Input
|
||||
|
||||
@@ -117,7 +117,7 @@ This is the heart of Control, you may put any image or even video here to be pro
|
||||
|
||||
Note below there are 2 other buttons, Inpainting and Outpainting, below.
|
||||
|
||||
|
||||
|
||||
|
||||
## ControlNet+
|
||||
|
||||
|
||||
+1
-1
@@ -5,7 +5,7 @@
|
||||
Native control module for SD.Next for Diffusers backend
|
||||
Can be used for Control generation as well as Image and Text workflows
|
||||
|
||||
For a guide on the options and settings, as well as explanations for the controls themselves, see the [Control Guide](https://github.com/vladmandic/automatic/wiki/Control-Guide) page.
|
||||
For a guide on the options and settings, as well as explanations for the controls themselves, see the [Control Guide](https://github.com/vladmandic/sdnext/wiki/Control-Guide) page.
|
||||
|
||||
## Supported Control Models
|
||||
|
||||
|
||||
+2
-2
@@ -6,7 +6,7 @@ SD.Next includes support for PyTorch-DirectML.
|
||||
|
||||
Add `--use-directml` on commandline arguments.
|
||||
|
||||
For details, go to [Installation](https://github.com/vladmandic/automatic/wiki/Installation#general-installation).
|
||||
For details, go to [Installation](https://github.com/vladmandic/sdnext/wiki/Installation#general-installation).
|
||||
|
||||
## Performance
|
||||
|
||||
@@ -34,4 +34,4 @@ Please report us via GitHub issue or Discord. (please check whether there's a du
|
||||
|
||||
## Olive (experimental support)
|
||||
|
||||
Refer to [ONNX Runtime](https://github.com/vladmandic/automatic/wiki/ONNX-Runtime-&-Olive)
|
||||
Refer to [ONNX Runtime](https://github.com/vladmandic/sdnext/wiki/ONNX-Runtime-&-Olive)
|
||||
|
||||
+1
-1
@@ -1,6 +1,6 @@
|
||||
# Docker
|
||||
|
||||
SD.Next includes basic [Dockerfile](https://github.com/vladmandic/automatic/blob/dev/Dockerfile) for use with **nVidia GPU** equipped systems
|
||||
SD.Next includes basic [Dockerfile](https://github.com/vladmandic/sdnext/blob/dev/Dockerfile) for use with **nVidia GPU** equipped systems
|
||||
Other system may require different configurations and base images, but principle remains
|
||||
|
||||
Goal of containerized SD.Next is to provide a fully stateless environment that can be easily deployed and scaled
|
||||
|
||||
+6
-6
@@ -8,7 +8,7 @@
|
||||
- [Schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell)
|
||||
Open-weight, timestep-distilled from Dev variation, available under Apache2.0 license
|
||||
|
||||
Additionally [SD.Next](https://github.com/vladmandic/automatic/) includes *pre-quantized* variations of **FLUX.1 Dev** variation: `qint8`, `qint4` and `nf4`
|
||||
Additionally [SD.Next](https://github.com/vladmandic/sdnext/) includes *pre-quantized* variations of **FLUX.1 Dev** variation: `qint8`, `qint4` and `nf4`
|
||||
Pick variant that uses less memory as model in original form has very high requirements
|
||||
|
||||
|
||||
@@ -16,17 +16,17 @@ Pick variant that uses less memory as model in original form has very high requi
|
||||
> [!IMPORTANT]
|
||||
> Allow gated access
|
||||
> This is a gated model, you need to accept the terms and conditions to use it
|
||||
> For more information see [Gated Access Wiki](https://github.com/vladmandic/automatic/wiki/Gated)
|
||||
> For more information see [Gated Access Wiki](https://github.com/vladmandic/sdnext/wiki/Gated)
|
||||
|
||||
> [!IMPORTANT]
|
||||
> Set offloading
|
||||
> Set appropriate offloading setting before loading the model to avoid out-of-memory errors
|
||||
> For more information see [Offloading Wiki](https://github.com/vladmandic/automatic/wiki/Offload)
|
||||
> For more information see [Offloading Wiki](https://github.com/vladmandic/sdnext/wiki/Offload)
|
||||
|
||||
> [!IMPORTANT]
|
||||
> Choose quantization
|
||||
> Check compatibility of different quantizations with your platform and GPU!
|
||||
> For more information see [Quantization Wiki](https://github.com/vladmandic/automatic/wiki/Quantization)
|
||||
> For more information see [Quantization Wiki](https://github.com/vladmandic/sdnext/wiki/Quantization)
|
||||
|
||||
> [!TIP]
|
||||
> Use reference models
|
||||
@@ -151,8 +151,8 @@ Link to [Flux Tools](https://blackforestlabs.ai/flux-1-tools/) announcement
|
||||
|
||||
To use, go to image or control interface and select *Flux Tools* in scripts
|
||||
All models are auto-downloaded on first use
|
||||
*note*: All models are [gated](https://github.com/vladmandic/automatic/wiki/Gated) and require acceptance of terms and conditions via web page
|
||||
*recommended*: Enable on-the-fly [quantization](https://github.com/vladmandic/automatic/wiki/Quantization) or [compression](https://github.com/vladmandic/automatic/wiki/NNCF-Compression) to reduce resource usage
|
||||
*note*: All models are [gated](https://github.com/vladmandic/sdnext/wiki/Gated) and require acceptance of terms and conditions via web page
|
||||
*recommended*: Enable on-the-fly [quantization](https://github.com/vladmandic/sdnext/wiki/Quantization) or [compression](https://github.com/vladmandic/sdnext/wiki/NNCF-Compression) to reduce resource usage
|
||||
- [Redux](https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev): ~0.1GB
|
||||
works together with existing model and basically uses input image to analyze it and use that instead of prompt
|
||||
*recommended*: low denoise strength levels result in more variety
|
||||
|
||||
+11
-11
@@ -10,7 +10,7 @@ After doing that, we decided that we would add everything else under the sun tha
|
||||
|
||||
This guide will attempt to explain how to use it so that anyone can understand it and put it to work for themselves.
|
||||
|
||||
Be sure to also check out [the Control resource page](https://github.com/vladmandic/automatic/wiki/Control) which has more technical information as well as some general tips and suggestions. Its usage information will be merged into this page soon™️.
|
||||
Be sure to also check out [the Control resource page](https://github.com/vladmandic/sdnext/wiki/Control) which has more technical information as well as some general tips and suggestions. Its usage information will be merged into this page soon™️.
|
||||
|
||||
We'll start with the... Control Controls!
|
||||
|
||||
@@ -18,11 +18,11 @@ We'll start with the... Control Controls!
|
||||
|
||||
#### Input
|
||||
|
||||
The Input control is exactly what it sounds like, it controls what input images (or videos) are contributing to your image generation, by default that is just the image in [Control input pane](https://github.com/vladmandic/automatic/wiki/control-guide#control-input), however if you select `Separate init image`, another image pane will appear below, allowing you to use that as well.
|
||||
The Input control is exactly what it sounds like, it controls what input images (or videos) are contributing to your image generation, by default that is just the image in [Control input pane](https://github.com/vladmandic/sdnext/wiki/control-guide#control-input), however if you select `Separate init image`, another image pane will appear below, allowing you to use that as well.
|
||||
|
||||
**Note:** When using a Control input image as well as a Init input image, the Init input dominates. Adjusting denoise to >=0.9 is recommended, as that will allow the Control input to balance with the Init input. Higher values will increase the strength of Control input further, giving it dominance.
|
||||
|
||||
|
||||
|
||||
|
||||
`Show Preview` is simple, it controls the visibility of the preview window in the far right of the middle row. You'll want this on if you're doing any kind of masking or manipulations that you would want to preview before generating.
|
||||
|
||||
@@ -41,7 +41,7 @@ There are 3 different Input types:
|
||||
This can be a little confusing at first because of the `Before` and `After` subtabs, however it's really quite simple and extremely powerful.
|
||||
The Control size menu allows you to manipulate the size of your input images before and after inference takes place.
|
||||
|
||||
|
||||
|
||||
|
||||
The `Before` subtab does 2 things:
|
||||
|
||||
@@ -59,7 +59,7 @@ The `After` subtab controls any upscaling or downscaling that would take place *
|
||||
|
||||
The Mask controls are where we start getting into the real meat of Control, not only does it allow a plethora of different options to mask, segment, and control the view of your masking with various preview types, but it comes with **22 different colormaps for your viewing pleasure!** (And I think vlad made some of those words up 🤫)
|
||||
|
||||
|
||||
|
||||
|
||||
- `Live update`: With this checked, your masking will update as you make changes to it, if this is off, you will need to hit the `Refresh` button to the right to have your preview pane update, making more changes to it while it is processing may lead to it being desynchronized, just hit the refresh button if it does not look correct.
|
||||
|
||||
@@ -69,7 +69,7 @@ The Mask controls are where we start getting into the real meat of Control, not
|
||||
|
||||
- `Auto-mask`: There are three options here, Threshold, Edge, and Greyscale. Each provides a different method of auto-masking your images.
|
||||
|
||||
- `Auto-segment`: Just like Auto-mask, we have provided an extensive list of [Auto-segmentation models](https://github.com/vladmandic/automatic/wiki/control#segmentation-models), they don't require ControlNet to handle the process, but may take a few seconds to process, depending on your GPU.
|
||||
- `Auto-segment`: Just like Auto-mask, we have provided an extensive list of [Auto-segmentation models](https://github.com/vladmandic/sdnext/wiki/control#segmentation-models), they don't require ControlNet to handle the process, but may take a few seconds to process, depending on your GPU.
|
||||
|
||||
- `Preview`: You can select the preview type here, we have provided 5 modes, Masked, Binary, Greyscale, Color, and Composite, which is the default.
|
||||
|
||||
@@ -87,7 +87,7 @@ The Video controls are quite exciting and fun to play with, with our tools now y
|
||||
With these simple controls, you can tweak your video output with surprising flexibility.
|
||||
Some video output methods provide more controls, try them all.
|
||||
|
||||
|
||||
|
||||
|
||||
- `Skip input frames`: This setting controls how many frames are processed from input instead of every frame. Setting it to 0 would mean processing every frame, a setting of 1 would process every other frame, a setting of 2 would process every third frame, cutting the number of total frames by 2/3rds, and so on.
|
||||
|
||||
@@ -113,19 +113,19 @@ This is the new home of our Vlad-created implementation of the AnimateDiff exten
|
||||
|
||||
***I honestly don't know how to use this, so I'll update this when I do. My apologies! But if you already do, enjoy!***
|
||||
|
||||
|
||||
|
||||
|
||||
#### IP-Adapter
|
||||
|
||||
This is our IP Adapter implementation, with 10 available models for your image or face cloning needs!
|
||||
|
||||
|
||||
|
||||
|
||||
### Image Panes
|
||||
|
||||
You may notice small icons above the image panes that look like pencils, these are Interrogate buttons. The left one is BLIP, and the right one is DeepBooru. Click one of the buttons to interrogate the image in the pane below it. The results will appear in your prompt area.
|
||||
|
||||
|
||||
|
||||
|
||||
#### Control Input
|
||||
|
||||
@@ -133,7 +133,7 @@ This is the heart of Control, you may put any image or even video here to be pro
|
||||
|
||||
Note below there are 2 other buttons, Inpainting and Outpainting, below.
|
||||
|
||||
|
||||
|
||||
|
||||
### ControlNet+
|
||||
|
||||
|
||||
+3
-3
@@ -1,12 +1,12 @@
|
||||
|
||||
|
||||
|
||||
|
||||
[](https://discord.gg/VjvR2tabEX)
|
||||
[](https://github.com/sponsors/vladmandic)
|
||||
|
||||
# Welcome to SD.Next
|
||||
|
||||
<div align="center">
|
||||
<img src="https://github.com/vladmandic/automatic/raw/master/html/logo-transparent.png" width=320 alt="SD.Next">
|
||||
<img src="https://github.com/vladmandic/sdnext/raw/master/html/logo-transparent.png" width=320 alt="SD.Next">
|
||||
</div>
|
||||
|
||||
## Step 1: Installation
|
||||
|
||||
+2
-2
@@ -20,7 +20,7 @@ Launch your preferred system terminal and navigate to the directory where you wa
|
||||
|
||||
**Clone SD.Next**
|
||||
Clone the repository by running following command in your desired location and then navigate into the cloned directory
|
||||
> `git clone https://github.com/vladmandic/automatic <optional directory name>`
|
||||
> `git clone https://github.com/vladmandic/sdnext <optional directory name>`
|
||||
|
||||
> [!TIP]
|
||||
> If you already have SD.Next installed and want to update to latest version, see [Update](Update) guide
|
||||
@@ -124,4 +124,4 @@ The server is finished launching when the console shows an entry for **"Startup
|
||||
|
||||
#### Python-for-MacOS
|
||||
|
||||
[See these instructions for Python on MacOS (and an explanation why it's unique).](https://github.com/vladmandic/automatic/wiki/MacOS-Python)
|
||||
[See these instructions for Python on MacOS (and an explanation why it's unique).](https://github.com/vladmandic/sdnext/wiki/MacOS-Python)
|
||||
|
||||
+4
-4
@@ -10,7 +10,7 @@
|
||||
|
||||
|
||||
> [!NOTE]
|
||||
> iGPUs are **not** supported with IPEX, use [OpenVINO](https://github.com/vladmandic/automatic/wiki/OpenVINO) if you want to use an iGPU.
|
||||
> iGPUs are **not** supported with IPEX, use [OpenVINO](https://github.com/vladmandic/sdnext/wiki/OpenVINO) if you want to use an iGPU.
|
||||
> Having an Intel iGPU can cause conflicts and random errors if you want to use a dedicated Intel GPU with IPEX.
|
||||
> Disable your iGPU (if any, e.g. UHD or Iris Xe) in the device manager.
|
||||
|
||||
@@ -21,7 +21,7 @@
|
||||
|
||||
- Install [Intel ARC Drivers](https://www.intel.com/content/www/us/en/download/785597/intel-arc-iris-xe-graphics-windows.html)
|
||||
- Install [Intel OneAPI Deep Learning Essentials](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit-download.html?packages=dl-essentials&dl-essentials-os=windows&dl-lin=offline)
|
||||
- Install [Git and Python](https://github.com/vladmandic/automatic/wiki/Installation#install-python-and-git)
|
||||
- Install [Git and Python](https://github.com/vladmandic/sdnext/wiki/Installation#install-python-and-git)
|
||||
- Open CMD in a folder you want to install SD.Next
|
||||
|
||||
|
||||
@@ -30,7 +30,7 @@
|
||||
Open a CMD window and install SD.Next from Github:
|
||||
|
||||
```shell
|
||||
git clone https://github.com/vladmandic/automatic
|
||||
git clone https://github.com/vladmandic/sdnext
|
||||
cd automatic
|
||||
```
|
||||
|
||||
@@ -103,7 +103,7 @@ cd ..
|
||||
Install SD.Next from Github:
|
||||
|
||||
```shell
|
||||
git clone https://github.com/vladmandic/automatic
|
||||
git clone https://github.com/vladmandic/sdnext
|
||||
cd automatic
|
||||
```
|
||||
|
||||
|
||||
+1
-1
@@ -87,7 +87,7 @@ Would mean apply LoRA to text-encoder with strength 0.1 on step 1 and then switc
|
||||
For any LoRA related issues, please follow the below procedure:
|
||||
- set environment variable `SD_LORA_DEBUG=true`
|
||||
- start SD.Next as usual and run it until problem occurs
|
||||
- create [GitHub issue](https://github.com/vladmandic/automatic/issues)
|
||||
- create [GitHub issue](https://github.com/vladmandic/sdnext/issues)
|
||||
- upload full `sdnext.log` as well as any console exception messages
|
||||
|
||||
### LoRA Loader
|
||||
|
||||
+2
-2
@@ -1,7 +1,7 @@
|
||||
# Models
|
||||
|
||||
List of popular text-to-image generative models with their respective parameters and architecture overview
|
||||
Original URL: <https://github.com/vladmandic/automatic/wiki/Models>
|
||||
Original URL: <https://github.com/vladmandic/sdnext/wiki/Models>
|
||||
|
||||
| Publisher | Model | Version | Size | Diffusion Architecture | Model Params | Text Encoder(s) | TE Params | Auto Encoder | Other |
|
||||
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
|
||||
@@ -43,7 +43,7 @@ Original URL: <https://github.com/vladmandic/automatic/wiki/Models>
|
||||
|
||||
## Notes
|
||||
|
||||
- Created using [SD.Next](https://github.com/vladmandic/automatic/) built-in model analyzer
|
||||
- Created using [SD.Next](https://github.com/vladmandic/sdnext/) built-in model analyzer
|
||||
- Number of parameters is proportional to model complexity and ability to learn
|
||||
Quality of generated images is also influenced by training data and duration of training
|
||||
- Size refers to original model variant in 16bit precision where available
|
||||
|
||||
+2
-2
@@ -72,7 +72,7 @@ Olive is an easy-to-use hardware-aware model optimization tool that composes ind
|
||||
|
||||
## How to
|
||||
|
||||
As Olive optimizes the models in ONNX format, you should set up [ONNX Runtime](https://github.com/vladmandic/automatic/wiki/ONNX-Runtime-%26-Olive/#how-to) first.
|
||||
As Olive optimizes the models in ONNX format, you should set up [ONNX Runtime](https://github.com/vladmandic/sdnext/wiki/ONNX-Runtime-%26-Olive/#how-to) first.
|
||||
|
||||
1. Go to `System` tab → `Compute Settings`.
|
||||
2. Select `Model`, `Text Encoder` and `VAE` in `Compile Model`.
|
||||
@@ -128,7 +128,7 @@ TBA
|
||||
|
||||
| Olive with DmlExecutionProvider | ROCm |
|
||||
|-------|------|
|
||||
|||
|
||||
|||
|
||||
|
||||
## Pros and Cons
|
||||
|
||||
|
||||
+2
-2
@@ -19,7 +19,7 @@ It is basically a TensorRT / Olive competitor that works with any hardware.
|
||||
### Preparations
|
||||
|
||||
- Install the drivers for your device
|
||||
- Install [Git and Python](https://github.com/vladmandic/automatic/wiki/Installation#install-python-and-git)
|
||||
- Install [Git and Python](https://github.com/vladmandic/sdnext/wiki/Installation#install-python-and-git)
|
||||
- Open CMD in a folder you want to install SD.Next
|
||||
|
||||
> [!NOTE]
|
||||
@@ -30,7 +30,7 @@ It is basically a TensorRT / Olive competitor that works with any hardware.
|
||||
Install SD.Next from Github:
|
||||
|
||||
```shell
|
||||
git clone https://github.com/vladmandic/automatic
|
||||
git clone https://github.com/vladmandic/sdnext
|
||||
```
|
||||
|
||||
Then enter into the automatic folder:
|
||||
|
||||
+8
-8
@@ -38,11 +38,11 @@ Generally speaking, for most GPUs our user-base has (mostly Nvidia on Windows ju
|
||||
|
||||
Good settings:
|
||||
|
||||
|
||||
|
||||
|
||||
Bad settings:
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
In general, using any of these selected "bad" settings is considered a bad thing, you only want to use any of these if necessary to make your card work with SD. They're slower and use up a lot more memory. *Unless you're on OpenVINO, things show up as fp32 there anyway due to how it works. Leave that alone*
|
||||
@@ -50,7 +50,7 @@ In general, using any of these selected "bad" settings is considered a bad thing
|
||||
That being said, if you are having strange issues with squares and whatnot and you're on something other than a newer Nvidia GPU (2000s and up?), you may wish to try these settings. Upcast sampling is the better version of --no-half, use it if at all possible.
|
||||
Try these one by one, unload the model, reload the model, then test generate, hopefully you will find one, or a combination that works.
|
||||
|
||||
|
||||
|
||||
|
||||
### Model Compile
|
||||
|
||||
@@ -86,11 +86,11 @@ You can easily use it at 0.3-0.4, performance goes up as the number does, going
|
||||
|
||||
**Default settings:**
|
||||
|
||||
|
||||
|
||||
|
||||
**Suggested settings:**
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
**Honestly, 0.5 and up is the real performance gain, but you test and decide yourself.**
|
||||
@@ -112,12 +112,12 @@ You may of course screw with the `swap size` and `UNet depth` as you like, I did
|
||||
|
||||
**Default settings:**
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
**Suggested settings:**
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
**Also has a quality impact, but I've never measured it personally**
|
||||
@@ -128,4 +128,4 @@ You may of course screw with the `swap size` and `UNet depth` as you like, I did
|
||||
Parallel process images in batch is intended for img2img batch mode.
|
||||
If you set batch size=n, typically it generates n images for each input, with this setting, it will generate 1 image for each input, but process n in parallel.
|
||||
|
||||
|
||||
|
||||
|
||||
+2
-2
@@ -41,7 +41,7 @@ Quantization can be done in multiple ways:
|
||||
|
||||
> [!TIP]
|
||||
> If you're on Windows with a compatible GPU, you may try **WSL2** for broader feature compatibiliy
|
||||
> See [WSL Wiki](https://github.com/vladmandic/automatic/wiki/WSL) for more details
|
||||
> See [WSL Wiki](https://github.com/vladmandic/sdnext/wiki/WSL) for more details
|
||||
|
||||
SD.Next supports multiple quantization engines, each with multiple quantization schemes:
|
||||
- `TorchAO`: 4 int-based and 3 float-based quantization schemes
|
||||
@@ -118,7 +118,7 @@ with optional platform-specific compute-optimization (available only on OpenVINO
|
||||
|
||||
- broad platform and GPU support
|
||||
- enable in *Settings -> Compute -> Compress model weights with NNCF*
|
||||
- see [NNCF Wiki](https://github.com/vladmandic/automatic/wiki/NNCF-Compression) for more details
|
||||
- see [NNCF Wiki](https://github.com/vladmandic/sdnext/wiki/NNCF-Compression) for more details
|
||||
|
||||
## Errors
|
||||
|
||||
|
||||
+5
-5
@@ -12,13 +12,13 @@ You can simply download these two files from Huggingface and place them into you
|
||||
To facilitate easy use of SD-XL and swapping between refiners, backends, and pipelines, we recommend selecting the
|
||||
following items in your Settings Tab, on the User Interface page:
|
||||
|
||||
|
||||
|
||||
|
||||
Once you select them, hit Apply settings, and then Restart server.
|
||||
When the server returns to being active and your browser page reloads, the Quicksettings
|
||||
at the top of your screen should look like this (assuming you were using SDXL):
|
||||
|
||||
|
||||
|
||||
|
||||
## VRAM Optimization
|
||||
|
||||
@@ -41,7 +41,7 @@ efficiently utilize VRAM. This is enabled when the following 3 options are Enabl
|
||||
|
||||
To use `Model Shuffling` do not have `--medvram` or `--lowvram` active, then use the following settings:
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
The important parts are the 3 Move checkboxes.
|
||||
@@ -63,7 +63,7 @@ Alternatively, you can enable the `Enable model CPU offload` checkbox in the `Se
|
||||
* VAE slicing (recommended)
|
||||
* Attention slicing is NOT recommended.
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
**VRAM Usage**: "Model CPU Offload" can work in 6 GB of VRAM.
|
||||
@@ -77,7 +77,7 @@ and cannot be used together with `--lowvram/Sequential CPU offload`
|
||||
If your GPU has as low as 2GB of VRAM, start your SD.Next session with `--lowvram` as a command line argument to **vastly** reduce
|
||||
VRAM requirements at the cost of even more inference speed. This is essentially the `Enable Sequential CPU offload` setting.
|
||||
|
||||
|
||||
|
||||
|
||||
Note: VAE slicing, VAE tiling, and Attention slicing are all enabled by `--lowvram` regardless of the checkboxes.
|
||||
|
||||
|
||||
+3
-3
@@ -12,17 +12,17 @@ StabilityAI's Stable Diffusion 3 family consists of:
|
||||
> [!IMPORTANT]
|
||||
> Allow gated access
|
||||
> This is a gated model, you need to accept the terms and conditions to use it
|
||||
> For more information see [Gated Access Wiki](https://github.com/vladmandic/automatic/wiki/Gated)
|
||||
> For more information see [Gated Access Wiki](https://github.com/vladmandic/sdnext/wiki/Gated)
|
||||
|
||||
> [!IMPORTANT]
|
||||
> Set offloading
|
||||
> Set appropriate offloading setting before loading the model to avoid out-of-memory errors
|
||||
> For more information see [Offloading Wiki](https://github.com/vladmandic/automatic/wiki/Offload)
|
||||
> For more information see [Offloading Wiki](https://github.com/vladmandic/sdnext/wiki/Offload)
|
||||
|
||||
> [!IMPORTANT]
|
||||
> Choose quantization
|
||||
> Check compatibility of different quantizations with your platform and GPU!
|
||||
> For more information see [Quantization Wiki](https://github.com/vladmandic/automatic/wiki/Quantization)
|
||||
> For more information see [Quantization Wiki](https://github.com/vladmandic/sdnext/wiki/Quantization)
|
||||
|
||||
> [!TIP] Use reference models
|
||||
> Use of reference models is recommended over manually downloaded models!
|
||||
|
||||
+2
-2
@@ -26,7 +26,7 @@ Creating custom themes can be done with minimal knowledge of `CSS` as each theme
|
||||
|
||||
Once you're happy with your theme, you can share it with the community by submitting a pull request that includes your CSS file!
|
||||
|
||||
- For Standard UI, create PR in [SDNext repo](https://github.com/vladmandic/automatic/pulls)
|
||||
- For Standard UI, create PR in [SDNext repo](https://github.com/vladmandic/sdnext/pulls)
|
||||
- For Modern UI, create PR in [ModernUI repo](https://github.com/BinaryQuantumSoul/sdnext-modernui/pulls)
|
||||
|
||||
But...If you're not comfortable with that, you can always share your theme in [Discussions](https://github.com/vladmandic/automatic/discussions)
|
||||
But...If you're not comfortable with that, you can always share your theme in [Discussions](https://github.com/vladmandic/sdnext/discussions)
|
||||
|
||||
+16
-16
@@ -52,20 +52,20 @@ See [User Themes](Theme-User) for details on creating custom themes
|
||||
|
||||
SD.Next comes with number of built-in themes:
|
||||
|
||||
- Black teal (default) 
|
||||
- Light teal 
|
||||
- Simple dark 
|
||||
- Simple light 
|
||||
- Black orange 
|
||||
- Black teal (default) 
|
||||
- Light teal 
|
||||
- Simple dark 
|
||||
- Simple light 
|
||||
- Black orange 
|
||||
|
||||
Following community created themes are included in SD.Next:
|
||||
|
||||
- Invoked 
|
||||
- Amethisyt nightfall 
|
||||
- Emerald paradise 
|
||||
- Midnight barbie 
|
||||
- Orchid dreams 
|
||||
- Timeless beige 
|
||||
- Invoked 
|
||||
- Amethisyt nightfall 
|
||||
- Emerald paradise 
|
||||
- Midnight barbie 
|
||||
- Orchid dreams 
|
||||
- Timeless beige 
|
||||
|
||||
### Modern Themes
|
||||
|
||||
@@ -74,11 +74,11 @@ Following community created themes are included in SD.Next:
|
||||
|
||||
### Gradio Themes
|
||||
|
||||
- Gradio default 
|
||||
- Gradio base 
|
||||
- Gradio soft 
|
||||
- Gradio glass 
|
||||
- Gradio monochrome 
|
||||
- Gradio default 
|
||||
- Gradio base 
|
||||
- Gradio soft 
|
||||
- Gradio glass 
|
||||
- Gradio monochrome 
|
||||
|
||||
Use of Gradio themes disables built-in theme engine and uses Gradio theme engine instead
|
||||
Gradio themes are not optimized for SDNext and will likely cause some UI components to look out of place
|
||||
|
||||
+2
-2
@@ -31,9 +31,9 @@ Additionally, check status of submodules:
|
||||
## Switching Branch
|
||||
|
||||
SD.Next development is done in multiple branches on GitHub:
|
||||
- Stable branch: [master](https://github.com/vladmandic/automatic)
|
||||
- Stable branch: [master](https://github.com/vladmandic/sdnext)
|
||||
Typically updated every several weeks after latest features have been tested
|
||||
- Development branch: [dev](https://github.com/vladmandic/automatic/tree/dev)
|
||||
- Development branch: [dev](https://github.com/vladmandic/sdnext/tree/dev)
|
||||
Updated regularly (e.g. daily) with latest features, fixes and changes
|
||||
This branch always contains latest patches, but it is not fully tested
|
||||
Once we decide on release schedule and consider it as sufficiently stable and tested,
|
||||
|
||||
+2
-2
@@ -109,7 +109,7 @@ Start from Windows using WSL shortcut or from command prompt:
|
||||
And then from *bash*:
|
||||
|
||||
> cd
|
||||
> git clone https://github.com/vladmandic/automatic/ sdnext
|
||||
> git clone https://github.com/vladmandic/sdnext/ sdnext
|
||||
> cd sdnext
|
||||
> ./webui.sh --debug
|
||||
|
||||
@@ -118,7 +118,7 @@ And then from *bash*:
|
||||
Starting SD.Next
|
||||
Logger: file="/home/vlado/sdnext/sdnext.log" level=DEBUG size=64 mode=create
|
||||
Python 3.10.12 on Linux
|
||||
Version: app=sd.next updated=2024-04-06 hash=e783b098 branch=master url=https://github.com/vladmandic/automatic//tree/master
|
||||
Version: app=sd.next updated=2024-04-06 hash=e783b098 branch=master url=https://github.com/vladmandic/sdnext//tree/master
|
||||
Platform: arch=x86_64 cpu=x86_64 system=Linux release=5.15.150.1-microsoft-standard-WSL2 python=3.10.12
|
||||
...
|
||||
nVidia CUDA toolkit detected: nvidia-smi present
|
||||
|
||||
+2
-2
@@ -65,10 +65,10 @@ The best place would be on an SSD for model loading.
|
||||
|
||||
In the Location Bar, type `cmd`, then hit [Enter]. This will open a Command Prompt window at that location.
|
||||
|
||||
|
||||
|
||||
|
||||
Copy and paste the following commands into the Command Prompt window, one at a time;
|
||||
`git clone https://github.com/vladmandic/automatic`
|
||||
`git clone https://github.com/vladmandic/sdnext`
|
||||
then
|
||||
`cd automatic`
|
||||
then
|
||||
|
||||
+1
-1
@@ -1 +1 @@
|
||||
© [SD.Next](https://github.com/vladmandic/automatic) - Check out [Docs site](https://vladmandic.github.io/sdnext-docs)
|
||||
© [SD.Next](https://github.com/vladmandic/sdnext) - Check out [Docs site](https://vladmandic.github.io/sdnext-docs)
|
||||
|
||||
Reference in New Issue
Block a user