Image Generation
Ongoing coverage on Image Generation.
Latest coverage
AMD presents new method of handing indirect lighting off to an image generation model: 'frame-by-frame' solution could be part of AMD's answer to DLSS 5 someday
AMD has published research detailing a new frame-by-frame method for generating global illumination using a one-step diffusion model, a technique that could potentially be integrated into future versions of their FidelityFX Super Resolution technology. This approach aims to create more realistic lighting by generating it via image generation models rather than computationally intensive methods like path tracing, though current performance metrics indicate it is still far from real-time gaming speeds.
Warhammer 40,000 Maker Games Workshop Confirms It Investigated 'A Few Human Errors' on Product Images to Make Sure Its Staff Hadn't Used AI
Games Workshop has stated that it investigated "human errors" in its product images to ensure its staff had not used artificial intelligence. The company confirmed it looked into a few instances where AI might have been inadvertently used in image depictions.
Meta's new Muse Image model accepts Instagram accounts as a prompt
Meta has introduced its new AI model, Muse, which can utilize Instagram accounts as a prompt for image generation. This technology is also being integrated into effects for Instagram Stories and image creation within WhatsApp.
Google expands personalized intelligence to Gemini app image creation
Google is expanding the personalized intelligence features of its Gemini app to include image creation capabilities. This update allows users to generate images directly within the Gemini application, leveraging advanced AI models.
A British MP is suing to see if xAI is legally responsible for the images Grok produces
xAI is facing investigations in the EU, UK, and California regarding its AI image generator, Grok. A British MP is seeking to determine xAI's legal responsibility for the images produced by its AI.
Google's Circle to Search feature can tell you if an image was AI-generated
Google is expanding its AI detection capabilities to more products, including the Circle to Search feature. This allows users to more easily verify if an image was generated or edited using artificial intelligence.
AI Yi-Yi!
Chinese AI firm SenseTime has released a new image generation model designed for speed. Meanwhile, the CEO of Electronic Arts stated that AI is not currently causing job losses in the industry, but rather assisting employees.
ChatGPT Images 2.0 is better at rendering non-Latin text
OpenAI has released ChatGPT Images 2.0, an updated image generation model with improved instruction following, text rendering, and object placement capabilities. The new system features reasoning abilities, allowing it to perform tasks like web searches and output verification. It shows significant gains in rendering non-Latin text and is more flexible with aspect ratios and resolution, making it potentially useful for game prototyping and storyboarding.
Gemini can now draw on your Google data to personalize the images it generates
Google's Gemini AI can now personalize image generation by drawing on user data from services like Google Photos, Gmail, Search, and YouTube. This "Personal Intelligence" feature aims to provide context for image creation, allowing users to generate images based on their personal information without explicit prompting. The feature is currently available for eligible AI Pro and AI Ultra subscribers in the Gemini app and will expand to other users soon.