OpenAI Blog
Jul 18, 2022
Reducing bias and improving safety in DALL·E 2
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.
DALL·E 2 pre-training mitigations
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.
Related stories
OpenAI Blog
May 18, 2022
DALL·E 2 research preview update
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.
OpenAI Blog
Aug 31, 2022
DALL·E: Introducing outpainting
Extend creativity and tell a bigger story with DALL·E images of any size.
OpenAI Blog
Jan 5, 2021
DALL·E: Creating images from text
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 AI
Sep 24
InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation
InGuard introduces an inner guardrail for text-to-image generation that operates within the model’s own representations, avoiding external classifiers. It grades prompts using the text encoder’s embeddings, modifies risky embeddings with SAGE to produce safe images, and employs a latent detector to halt generation early. Evaluated on the RevGen Safety Benchmark, InGuard achieves a 97.9–98.8% safety rate across five open-weight models while reducing benign disturbances, model parameters, and denoising steps.
arXiv AI
Jul 8
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
arXiv:2607. 05910v1 Announce Type: cross Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image.
arXiv AI
Aug 19
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization
DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.
arXiv AI
Jun 26
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
arXiv:2606. 27147v1 Announce Type: cross Abstract: Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens.
arXiv Machine Learning
Jun 17
Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models
arXiv:2403. 18957v3 Announce Type: replace-cross Abstract: Online user generated content games (UGCGs) are increasingly popular among children and adolescents for social interaction and more creative online entertainment.
arXiv AI
Jun 12
Reconstructing Template-Memorized Images from Natural Prompts
arXiv:2507. 07947v4 Announce Type: replace-cross Abstract: Recent advances in generative models, such as diffusion models, have raised concerns related to privacy, copyright infringement, and data stewardship.
arXiv AI
Aug 25
GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration
arXiv:2608.21869v1 Announce Type: cross Abstract: Text-to-image (T2I) diffusion models offer powerful visual generation, but their controllability creates a critical safety challenge: adversarial pro...
Hugging Face Trending Papers
Jun 25
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens. These tokens are derived from a codebook that maps embeddings to quantized visual patterns.