dalle-2-preview/system-card.md at main · openai/dalle-2-preview

Targeted harassment, bullying, or exploitation of individuals is a principal area of concern for deployment of image generation models broadly and Inpainting in particular.Inpainting – especially combined with the ability to upload images – allows for a high degree of freedom in modifying images of people and their visual context. While other image... See more

The model can generate known entities including trademarked logos and copyrighted characters. OpenAI will evaluate different approaches to handle potential copyright and trademark issues, which may include allowing such generations as part of "fair use" or similar concepts, filtering specific types of content, and working directly with copyright/tr... See more

DALL·E 2 currently has a very limited ability to render legible text. When it does, text may sometimes be nonsensical and could be misinterpreted. It’s important to track this capability as it develops, as image generative models may eventually develop novel text generation capabilities via rendering text.

An interesting cause of spurious content is what we informally refer to as "reference collisions": contexts where a single word may reference multiple concepts (like an eggplant emoji), and an unintended concept is generated. The line between benign collisions (those without malicious intent, such as "A person eating an eggplant") and those involvi... See more

OpenAI reached out to researchers and industry professionals, primarily with expertise in bias, disinformation, image generation, explicit content, and media studies, to help us gain a more robust understanding of the DALL·E 2 Preview and the risk areas of potential deployment plans. Participants in the red team were chosen based on areas of prior ... See more

Despite the pre-training filtering, DALL·E 2 maintains the ability to generate content that features or suggests any of the following: nudity/sexual content, hate, or violence/harm.

While we are highly uncertain which commercial and non-commercial use cases might get traction and be safely supportable in the longer-term, plausible use cases of powerful image generation and modification technologies like DALL·E 2 include education (e.g. illustrating and explaining concepts in pedagogical contexts), art/creativity (e.g. as a bra... See more

The default behavior of the DALL·E 2 Preview produces images that tend to overrepresent people who are White-passing and Western concepts generally. In some places it over-represents generations of people who are female-passing (such as for the prompt: “a flight attendant” ) while in others it over-represents generations of people who are male-pass... See more

In principle any image generated by DALL·E 2 could have been drawn by hand, edited from existing images using tools, or recreated with hired models and photographers; this speed (and cost) differential is a difference in degree that may add up to a difference in kind.

As noted above, not only the model but also the manner in which it is deployed and in which potential harms are measured and mitigated have the potential to create harmful bias, and a particularly concerning example of this arises in DALL·E 2 Preview in the context of pre-training data filtering and post-training content filter use, which can resul... See more