12 stories tagged Image Generation
A new study on arXiv introduces a membership inference attack (MIA) for fine-tuned discrete diffusion language models (dLLMs), revealing that attackers can efficiently determine if specific data was used in fine-tuning. This poses significant privacy risks for users of AI systems built on these models.
Meta’s new Muse Image model can add real people—like your Instagram friends—into AI-generated photos. This feature is already live in Meta AI, Instagram, and WhatsApp, with Facebook and Messenger coming soon.
Microsoft has integrated DALL-E 3 into Bing Image Creator, making it easier for users to generate high-quality images. This update enhances creativity and accessibility for everyday users.
Apple has significantly improved its Image Playground tool, making it more competitive with other AI image generators. The updates include better image quality, more creative options, and a smarter prompt-understanding system.
Adobe’s new conversational AI agent for image generation is different from other tools because it actually involves you in the creative process. It’s like having a junior design intern who needs your input and guidance—but one that is still mediocre and requires a lot of direction. This could change how non-designers approach creative projects, but it's not a magic bullet.
A new study reveals a simple method to bypass safety filters in AI image generators. The technique, called PAST2HARM, uses past tense prompts to trick models into creating harmful content.
InkTag.io is a new AI tool that generates images matching your brand's style, colors, and logo. It solves the problem of finding or creating on-brand visuals for blogs and social media.
Google's Nano Banana 2 integrates personal context and Google Photos to create customized images. This enhances the Gemini app's ability to generate highly personalized content.
OpenAI’s updated image generator, ChatGPT Images 2.0, now pulls information from the web to create more sophisticated images. This new feature allows for more detailed and accurate AI-generated art based on single prompts.
OpenAI has launched GPT Image 2, a new AI model capable of generating high-quality images from text prompts. The model represents a significant leap in AI-driven image creation.
OpenAI's new ChatGPT Images 2.0 model excels not just in image generation but also in producing coherent text. This marks a significant leap in AI versatility and integration.
OpenAI has released a guide on using ChatGPT to create and refine images through clear prompts. The guide highlights the efficiency and creative potential of AI-driven visual content generation.