Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-19 17:24:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

update 

Signed-off-by: Vladimir Mandic <mandic00@live.com>
Vladimir Mandic
2025-01-10 08:20:35 -05:00
parent ba50d70e47
commit 7c2400e9dc
1 changed files with 26 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Control-HowTo.md
+26 -16
@@ -5,7 +5,8 @@ ControlNet, from its name, can "control" the Diffusion model you are using and f
These models can influence the image in different ways: for example, you can pose people or characters, draw a scene basing on spatial information (how far is a person from a car behind, for example), on pre-existing lineart, and so on. They work by supplying a "control image" (which can be pre existing, or created on the fly before generation) which represents in a special way the information the ControlNet model needs.
> [!NOTE]
> Using ControlNet comes at a price of a *lower generation speed and an increased VRAM usage.*
> *ControlNet models can be large*
> *Using ControlNet decreases generation speed and increases resource usage, especially GPU VRAM*
## The choice of model
@@ -59,51 +60,60 @@ Several examples of the available software that can be used to generate controln
## Using ControNet with SD.Next
> [!NOTE]
> Following step-by-step guide is created using SD.Next ModernUI
> Same options exist in StandardUI as well althrough their location in the UI may differ
First, enable **Control** by clicking on the "Control" checkbox near the preview area.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/da580910-6c4a-4ad4-b310-b2dc564a37c9)
A new tab will appear, make sure "ControlNet" is selected.
A new tab will appear, make sure "ControlNet" is selected.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/15232b45-3158-4257-ae99-d512dc9a449d)
Now you have to decide how many "units" (ControlNet models) to use. For most uses one is sufficient, but for particularly complex scenarios you may need more than one. You can control the number of units by increasing the "Units" number. This guide assumes you use one unit. The workflow is the same the more units you add. Bear in mind that the more units you use, the more VRAM will be used.
Now you have to decide how many "units" (ControlNet models) to use. For most uses one is sufficient, but for particularly complex scenarios you may need more than one. You can control the number of units by increasing the "Units" number. This guide assumes you use one unit. The workflow is the same the more units you add. Bear in mind that the more units you use, the more VRAM will be used.
<TBD:IMAGE>
![immagine](https://github.com/user-attachments/assets/204af4ff-07f0-442a-874d-4037c35a15f0)
Ensure the unit is enabled by checking if the checkbox under "ControlNet Unit 1" is checked. If it is not, click on it to enable it.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/18caf392-1001-4b97-8da5-d622457d3a2f)
Now you have to select the ControlNet model you want to use. Click on the "reload" icon to load the available ControlNet models and select the one you want from the list. It will be automatically downloaded and made available to SD.Next. You can check the console output or the log for progress information.
Now you have to select the ControlNet model you want to use. Click on the "reload" icon to load the available ControlNet models and select the one you want from the list. It will be automatically downloaded and made available to SD.Next. You can check the console output or the log for progress information.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/04a347e7-c5c4-49c1-bc83-dfdaa6ecf434)
![](https://github.com/user-attachments/assets/0e3f57f7-d3a6-4b0c-ab5f-7f0ea083c311)
> [!NOTE]
> No items will display unless you have loaded a checkpoint first.
Should you want to use a preprocessor, select it from the list next to the ControlNet combo box.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/84e9b362-4ebb-40b4-9fe2-cc0bb4d8825c)
Now you have to decide how much your ControlNet model will affect the generation. The "CN" strength slider goes from 0 (no effect) to 1 (complete effect). You might want to experiment here depending on your needs: for OpenPose models, 1 is usually fine, but for depth and canny, lower strength may be required.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/0c8d0dd1-29d2-4f7d-a811-c3a46ae82e88)
For specific uses (out of scope of this guide) you can also decide for how long ControlNet will be active during the generation process. This can be adjusted by changing the values on "CN start" and "CN end" (0, start of the generation, 1 end).
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/a6452ac9-0276-4749-8a9d-6c681bd07c11)
Click on the upper arrow icon to upload your control image. **Note**: if you don't use a preprocessor it *must* be in the same aspect ratio as the image that will be generated.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/d8d77008-237a-410f-ac20-b9de4c979cb5)
If you have used a preprocessor, you can hit the preview icon to see how the image will be preprocessed.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/ab39ea90-6f9f-45b8-bf39-7e4c822c966a)
Specific preprocessor settings can be changed in the Processor settings tab.
<TBD:IMAGE>
![](https://github.com/user-attachments/assets/a0e30ca7-f563-41c8-afe9-69d5ae7a58cd)
> [!TIP]
> If you have messed up, hit the "Reset" icon and the values will be all reset to default.
Once everything is set up, hit Generate. You will get a preview of your control image and generation will begin.
Once everything is set up, write your prompt, set your image parameters, and hit Generate. You will get a preview of your control image and generation will begin.