Today, we are implementing a new technique so that DALL·E generates images of people that more accurately reflect the diversity of the world’s population.
In order to share the magic of DALL·E 2 with a broad audience, we needed to reduce the risks associated with powerful image generation models. To this end, we put various guardrails in place to prevent generated images from violating our content policy.
Early users have created over 3 million images to date and helped us improve our safety processes. We’re excited to begin adding up to 1,000 new users from our waitlist each week.
arXiv:2606. 05188v1 Announce Type: cross Abstract: (Gen)AI diversity is not merely an ethical issue.
Extend creativity and tell a bigger story with DALL·E images of any size.
arXiv:2607. 24898v1 Announce Type: cross Abstract: State-of-the-art toxicity detectors for text-to-image generation adopt a one-size-fits-all approach: a single universal model applying fixed safety guidelines to all users.
arXiv:2508. 03483v3 Announce Type: replace-cross Abstract: While prior research on text-to-image generation has predominantly focused on biases in human depictions, demographic bias in generated objects remains relatively underexplored.
We’ve trained a neural network called DALL·E that creates images from text captions for a wide range of concepts expressible in natural language.
arXiv:2607. 22745v1 Announce Type: cross Abstract: Rapid advances in image generation are eroding the evidentiary value of visual content in settings where authenticity can affect public safety and personal reputation.
arXiv:2601. 04946v3 Announce Type: replace-cross Abstract: Automatic metrics are widely used to evaluate text-to-image models, often replacing human judgment in benchmarking, model selection, and large-scale data filtering.
arXiv:2607. 14962v1 Announce Type: cross Abstract: Text-to-image (T2I) models can synthesize realistic, prompt-aligned images, yet samples generated for the same prompt often cover only a small subset of visually distinct modes.
Text-to-image (T2I) models have been shown to exhibit social biases. Prior work has mainly focused on gender, skin tone, and cultural representation within restricted occupational associations, and emerging benchmarks increasingly incorporate these dimensions.
arXiv:2606. 00369v1 Announce Type: cross Abstract: Safe global deployment of AI models requires alignment with human values that vary across cultures.