SD-2.1
PulseAugur coverage of SD-2.1 — every cluster mentioning SD-2.1 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Text-to-image AI models show persistent gender bias, research finds
A new research paper published on arXiv reveals that text-to-image AI models, including various generations of Stable Diffusion, exhibit significant gender stereotyping across occupations. The study found that 76.4% of …
-
New AEGIS defense tackles visual synonym attacks in text-to-image models · 3 sources tracked
Researchers have developed AEGIS, a novel defense mechanism designed to combat visual synonym attacks (VSA) in text-to-image diffusion models. Unlike previous methods that focus on explicit unsafe concepts, AEGIS dynami…
-
EquiSteer method reduces bias in text-to-image models without retraining
Researchers have developed EquiSteer, a novel method to reduce demographic biases in text-to-image generation models without requiring retraining. This technique operates at inference time by steering cross-attention ac…