Too Long; Didn't Read
Imagic takes such a diffusion-based model able to take text and generate images out of it and adapts the model to edit the images. You can generate an image and then teach the model to edit it any way you want. Imagic: Text-Based Real Image Editing with Diffusion Models. ArXiv preprint arXiv: 2210.09276. Use it with Stable Diffusion: https://://://www.louisbouchard.ai/imagic/