What Is a Diffusion Model?

Diffusion models work by training on billions of images and learning to reverse a 'diffusion' process that gradually adds noise to images. At inference, the model starts with noise and removes it step by step, guided by a prompt, to generate a new image. Applied to personal content, fine-tuned diffusion models can create photorealistic images of real individuals using nothing more than facial reference photos. The resulting images, despite being entirely synthetic, are relevant to considerations of face exposure.

Key facts about this term

1. Fine-tuning makes diffusion models target-specific A general diffusion model can be fine-tuned on 10-20 photos of a specific person to generate highly realistic images of that person. This is the most common technical method used to create synthetic representations.
2. Open-source diffusion models are widely accessible Stable Diffusion and its derivatives are freely downloadable and can be run locally without any platform oversight. This makes detection and prevention challenging without clarity on the law.
3. The output is relevant regardless of the model used Whether generated by a commercial API or a locally-run open-source model, images of real identifiable individuals are relevant for face exposure considerations.