Topic
image generation
Technology Hugging Face Faces Widespread Deepfake Nudes Problem on Its AI Platform
A new report from AI Forensics reveals that Hugging Face, the multibillion-dollar open-source AI repository, is widely used to generate nonconsensual deepfake nude images. Researchers found that 7 of 9 top image-editing Spaces easily produced topless images, and 73% of prompts on honey-pot Spaces were sexual in nature. The platform has content policies but appears to lack platform-level safeguards, raising questions about moderation.
Meta Faces Privacy Backlash Over AI Tool That Generates Images from Public Instagram Profiles
Meta's new AI image generator, Muse Image, allows users to create pictures using other people's public Instagram profile pictures without telling them. Privacy groups and regulators have criticised the feature, warning it facilitates non-consensual AI-altered images. Meta says users can opt out via a separate setting.
FreeStyle: Scalable Style-Content Dual-Reference Generation via Community LoRA Mining
FreeStyle is a scalable dual-reference generation framework that leverages community LoRAs as compositional anchors for style and content. It introduces a two-stage curriculum with attention-level enrichment and frequency-aware RoPE modulation to suppress leakage from style references. The framework is evaluated on a new benchmark covering style similarity, content preservation, and leakage rejection, achieving a strong balance among these objectives.
MakeupMirror Model Boosts Facial Attribute Preservation in Diffusion-Based Makeup Transfer
Researchers propose MakeupMirror, a diffusion-based makeup transfer model that preserves facial identity and skin tone better than previous solutions. It achieves 60% higher facial recognition similarity, 50% lower skin tone difference, and 0.7s latency, with 94% expert acceptance, advancing virtual try-on for e-commerce.
New Research Provides Conditional Diffusion Guidance Under Hard Constraints for AI
A research paper proposes a framework for conditional generation in diffusion models under hard constraints, using Doob's h-transform and martingale-based learning algorithms. The method guarantees constraint satisfaction with probability one, targeting safety-critical applications and rare-event simulation.
STAR Allocation Method Improves Text-to-Image AI Training with Spatiotemporal Rewards
A new method called SpatioTemporal Adaptive Reward (STAR) Allocation improves reinforcement learning post-training for text-to-image generation. By using text-image attention to allocate rewards to relevant latent regions, STAR enhances compositional semantic alignment, text rendering, and preference optimization without changing the external reward source. The method was validated on Stable Diffusion 3.5 Medium, achieving top scores on GenEval, OCR, and PickScore benchmarks.
Technology Apple Intelligence Now Generates Fake Images with Google Models at WWDC 2026
Apple Intelligence, running on iOS 27 Dev Beta, now includes generative AI image editing tools that can create or infer missing content, such as a child's sock. The features, unveiled at WWDC 2026, leverage off-device models built with Google. Tools include enhanced Clean Up, Spatial Reframing, and an expansion tool.