I am attempting to fine-tune the stable diffusion with Dreambooth on myself (my face and body), but the results are not satisfactory. I am seeking guidance on the best way to fine-tune stable diffusion in order to generate images of myself in various settings, such as sitting in a cafe or swimming at the beach.
I have been experimenting with various prompts and images for fine-tuning, but the results have been poor. I would like to understand what types of images I should use for fine-tuning, whether it be just the face, just the body, or both, and what to include in the prompt during and after the fine-tuning process.
I recommended this video, try using different photos to train your model and different descriptions, like this: Close portrait of elegant [here name of class] thin face person in tailored suit- futurist style, intricate baroque detial, elegant, glowing lights, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by wlop, mars ravelo and greg rutkowski.