Image Generation

Today's Stories

1. 1

   AI Summit 2026 session applications open June 29

   The JAPAN & AI SUMMIT 2026 by FLUX announced that session applications will open on June 29 (Monday), and released session outlines and additional speaker names. The summit is a key platform for businesses to learn about AI developments and connect with industry leaders; the public session details and speaker roster help attendees plan their participation.

   Interested participants should mark June 29 as the date applications become available to secure their spot at the event.

2. 2

   Black Forest Labs on image generation shift from diffusion to flow matching

   Dustin Podell, cofounder and researcher at Black Forest Labs, discussed the evolution of AI image generation technology in a Practical AI Podcast episode, explaining the progression from diffusion models to flow matching and how modern image models work for editing and visual workflows. Image generation has advanced dramatically over the past three to four years—from producing blurry, vaguely related outputs to generating photorealistic content that can be used in short films and professional workflows. The core technology has improved significantly while remaining conceptually grounded in transformer-based approaches introduced in 2017, making visual AI increasingly practical for real-world applications.

   The episode covers the FLUX family of models and local image generation techniques. Black Forest Labs' work on flow matching and in-context image editing represents the technical direction the field is moving, with implications for developers and businesses building visual workflows.

3. 3

   FluidVoice: open-source voice-to-text app for macOS with local AI

   FluidVoice is an open-source voice-to-text dictation application for macOS that processes speech using local AI models, meaning the audio processing happens on your computer rather than being sent to a remote server. For macOS users who want dictation or voice input, this offers a privacy-focused alternative—your voice data stays on your device instead of being transmitted to a cloud service. The open-source model also means developers can inspect and modify the code, which can build trust in how the tool works.

   The project is available on GitHub (altic-dev/FluidVoice), where you can download, inspect, and contribute to it. As an early-stage open-source tool, its practical maturity and ease of use for non-technical users remain to be seen.

4. 4

   WordPress sites can now connect directly to AI tools

   A new service enables self-hosted WordPress sites to integrate with AI systems. The offering connects WordPress installations to AI capabilities without requiring users to leave their site. WordPress powers a large portion of websites globally. Direct AI integration could let site owners add AI features—such as content generation or automation—without building custom connections or relying on third-party plugins with uncertain maintenance.

   The service is available at wpvibe.ai/start/. Business owners running WordPress sites can explore whether this integration fits their workflow and feature needs.

5. 5

   More on the depolarizing effects of current AI

   More on the depolarizing effects of current AI

6. 6

   Google launches Gemini 3.1 Flash-Lite for fast, cheap image generation

   Google unveiled Nano Banana 2 Lite (designated Gemini 3.1 Flash-Lite Image) today, positioning it as the fastest and most cost-effective option in its image generation lineup. The model generates images in 4 seconds at $0.034 per 1,000 images and is available immediately to enterprise developers through Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform. The move targets businesses with tight infrastructure budgets that need rapid image generation. By bundling the tool with Google's larger Workplace and AI offerings, the company aims to make AI-powered creative work accessible to enterprises at lower cost than competitors.

   The model trades some speed and customization against startup Krea's new Krea 2 Turbo, which offers open modification and commercial usage rights. This release lands alongside a public preview of Gemini Omni Flash, Google's multimodal model.