How To Turn Yourself Into Pixar Character Using Stable Diffusion AI

Image by Jim Clyde Monge

Whether you want to be the next Woody, the next Buzz Lightyear, or turn your fish into the next Nemo, Stable Diffusion can make it happen. With this latent text-to-image diffusion model, you can turn yourself into any Pixar character's look with just a simple text prompt.

In this article, I’m going to show you how you can run Stable Diffusion on your local PC and perform fun experiments with the AI model completely free.

What You’ll Need

• Nvidia GPU with at least 4GB of VRAM
• Stable Diffusion Web UI — Download the project from GitHub
• Stable Diffusion v1.5 checkpoint file — Download from Hugging Face
• A portrait photo of you

Setup The Environment

1. Extract the downloaded Stable Diffusion project file to your local disk. The file list should look like this.

Image by Jim Clyde Monge

2. Rename the checkpoint file to “model.ckpt” and paste it inside the models\Stable-diffusion folder.

Image by Jim Clyde Monge

3. Finally, double-click the “webui-user.bat” file in cmd.

Image by Jim Clyde Monge

If you run into a python not found error, make sure to put the python.exe location in the webui-user.bat file.

Image by Jim Clyde Monge

Open http://127.0.0.1:7860/ in your Chrome browser to launch the Gradio UI. It should look something like this.

Image by Jim Clyde Monge