Upload your input image, then you can put the image prompt between the two prompts

"turn the image into

<your prompt here>

while preserving the outlines and shapes of the original image"

See examples on my model itself

I highly suggest editing your input image with the prompt "turn the image into a black and white stencil against a white background" then run that image through this model. If your image is too human like it will likely just try to generate a human, even if you stencil it. It is very picky about prompt and picture choice as this is not a controlnet but a LoRa. I just checked and my dataset actually contains zero QR codes, so that will be a priority for V2. For tricker images/prompts I suggest fewer steps, higher CFG, higher strength.