As we all know, the Canny function in ControlNet can accurately extract lines from the original image, but unfortunately, it cannot perform color transfer. This LoRA attempts to change this. It can not only achieve line extraction similar to Canny, but also extract the main colors from the original image and transfer them to the new image, thereby forming a new visual style.

Fields where this LoRA is suitable for application:

The production of memes

Nostalgic comics

Vector style illustrations

Instruction manual illustrations

It is also proficient in drawing complex structures/scenes

This LoRA is divided into the Base version and the Plus version. The Base version is shared for free on Civitai, while the Plus version is for my own use. It was trained with more computing power, so it is only available to my members. you can check it here get it

Supports input in multiple styles:

Whether it's realistic photos, film and television stills, 3D, 2.5D, 2D illustrations, or even AI-generated images, they can all achieve migration very well.

The differences between the Base version and the Plus version:

More accurate restoration of appearance

More abundant details

More accurate understanding of the background

The Plus version can be obtained on my patreon page

end - credit scene

If you feel that the output image is too flat, you can use the prompt "rick details" to add more detailed effects.

OK! That's all

If you think my works are good, you are welcome to join my Patreon to get more private models. 🤖I also accept private customization🤖

Thank you for reading up to here. English is not my native language. The above is translated by AI. If there is anything inappropriate, welcome to correct me. Finally, I hope you have fun！

👉👉👉My CivitAI homepage👈👈👈