With Pose Lock (also called ControlNet), you can upload a source image to influence your AI image generations.

You can use this feature to do a bunch of cool things like maintaining compositions, copying poses, and transforming art styles. And it all depends on the setting you choose.

Each setting creates a unique ‘map’ of a source image. This ‘map’ tells the Model how the image it generates should be composed or oriented.

Let’s take an example to understand this better. We’re going to use the image below in the ControlNet and experiment with different preprocessors and prompts to see what we can create.

<aside> 💡 Pro Tip: For SD1.5 & SDXL try to select an aspect ratio that matches your source image to avoid cropping or distorting in your generated images.

</aside>

ControlNet source image

Maintain an image’s composition with Depth and Canny

(Depth and Canny work with all models, including FLUX)

The Depth preprocessor maintains 3D composition of an image.

Control Map made by the Depth preprocessor

Model: NightVisionXL Prompt: a man sitting, beach in the background, hyper realistic, masterpiece, uhd, canon eos 5d