Tag

Image Editing

All articles tagged with #image editing

Grok on X Generates Millions of Sexualized Images, CCDH Finds
technology1 month ago

Grok on X Generates Millions of Sexualized Images, CCDH Finds

CCDH estimates that Grok, X’s image-editing AI, produced about 3.0 million sexualized, photorealistic images (roughly 23,338 of children) over 11 days after the feature’s launch, at a pace of ~190 images per minute, based on a 20,000-post sample across 4.6 million image posts. About 29% of the child-sexualized images remained accessible as of mid-January, and 9,936 non-photorealistic child images were also generated; all identified cases were reported to the Internet Watch Foundation. The analysis used AI-assisted detection with manual review and provides 95% uncertainty intervals for prevalence estimates.

Reviving Vintage Memories: Colorize and Restore Old Photos with AI
technology1 month ago

Reviving Vintage Memories: Colorize and Restore Old Photos with AI

A practical guide showing how to digitize old photos and use generative AI (notably Adobe Firefly) to colorize and repair them. It covers scanning or photographing images, choosing an AI tool, uploading one image at a time, and giving precise prompts to fix blemishes, remove text, crop, and colorize. The article emphasizes a staged, iterative workflow and warns that results may require refinements to avoid unwanted changes.

Apple Develops Unified AI Model for Vision, Creation, and Editing
technology2 months ago

Apple Develops Unified AI Model for Vision, Creation, and Editing

Apple researchers have developed UniGen-1.5, a unified AI model capable of understanding, generating, and editing images within a single system, enhancing previous models with new editing capabilities and improved instruction alignment, achieving state-of-the-art performance on various benchmarks, though it still faces challenges with text generation and identity consistency.

Google Unveils Gemini 2.5 Flash Image for Advanced AI Image Editing
technology6 months ago

Google Unveils Gemini 2.5 Flash Image for Advanced AI Image Editing

Google has upgraded its AI image model to Gemini 2.5 Flash Image, enhancing its ability to generate, merge, and edit images with greater precision and consistency, aiming to compete with industry leaders like OpenAI. The model, initially dubbed 'nano-banana' during testing, now offers users advanced editing capabilities through natural language prompts and is accessible via various Google platforms and APIs.