Hi guys, this is my first article on TensorArt.
Have you ever found it difficult to make a difficult pose for a character such as dancing?
Even though you used many specific words to describe it, but it seem like AI don't understand your prompt
Today I will introduce to you the control_net that will make your "AI life" easier than ever. ^o^
That is control_net openpose
![](https://image.tensorartassets.com/article/627264039524954437/bc5341c4-9343-4433-bd5a-202fd5e9b373.png)
How to use?
It's very simple.
Let say you wanna make a ballet dancer
1/ Go to the "Add control net" option
![](https://image.tensorartassets.com/article/627264039524954437/d544e136-317f-43f7-8730-07811c23858a.png)
2/Upload the image sample you have, then select the working model of control_net (for ex: openpose)
![](https://image.tensorartassets.com/article/627264039524954437/c9879fba-9615-41e5-98ec-0155d2d07bce.png)
3/ Then wait for the result
![](https://image.tensorartassets.com/article/627264039524954437/a576dd07-866b-451d-a682-b7dcafc2f134.png)
One more example with akimbo pose, with in my opinion is very hard for AI to understand
![](https://image.tensorartassets.com/article/627264039524954437/4f30e481-dfca-4ecb-a751-d1a7af2f60d9.png)
![](https://image.tensorartassets.com/article/627264039524954437/9c11d062-abf4-4d0b-97b6-8bf7ffea5202.png)
Of course, because this is a very basic controlnet pose, it is understandable that the accuracy is not high.
In the next article, I will show you a more advanced option called control_depth, which helps you achieve results 10 times more accurate than openpose.