AI-generated synthetic images are created entirely by AI from text prompts or other inputs, using diffusion models like Stable Diffusion, Midjourney, and DALL-E. The image isn’t a manipulation of a real photo; it’s fabricated from scratch.

Content advisory: this technique is used to produce AI-generated child sexual abuse material (CSAM), including sexual imagery of real children and fully synthetic depictions. Creating, possessing, or sharing this material is illegal. Report suspected CSAM to the NCMEC CyberTipline at report.cybertip.org.

• A text prompt or reference image is fed to a generative model
• The model outputs a photorealistic image matching the prompt
• Recent models match human-perceived quality of professional photography for most subjects

• Fake news imagery accompanying disinformation campaigns
• Fraudulent product images used in marketplace listings
• Synthetic damage photos submitted in insurance claims
• Manufactured visual evidence in legal disputes or HR cases
• Fake property photos in real estate or rental scams