DALL·E 2 began as a research project and is now available in beta. Safety mitigations we have developed and continue to improve upon include:
Preventing harmful generations
We’ve limited the ability for DALL·E 2 to generate violent, hate, or adult images. By removing the most explicit content from the training data, we minimized DALL·E 2’s exposure to these concepts. We also used advanced techniques to prevent photorealistic generations of real individuals’ faces, including those of public figures.
Read about improving safety
Curbing misuse
Our content policy does not allow users to generate violent, adult, or political content, among other categories. We won’t generate images if our filters identify text prompts and image uploads that may violate our policies. We also have automated and human monitoring systems to guard against misuse.
Read content policy(opens in a new window)
Phased deployment based on learning
Learning from real-world use is an important part of developing and deploying AI responsibly. We began by previewing DALL·E 2 to a limited number of trusted users. As we learned more about the technology’s capabilities and limitations, and gained confidence in our safety systems, we slowly added more users and made DALL·E available in beta in July 2022.
View risks and limitations(opens in a new window)