Midjourney just rolled out its V8.2 image model, zeroing in on elevated aesthetics and deeper personalization. The update promises bolder, edgier generations while dramatically cutting down on random low-quality outputs. Thanks to an expanded pool of community ratings, it now mirrors individual artistic taste far more accurately.
Microsoft just launched public previews for MAI-Image-2.5-Pro and MAI-Voice-2-Flash, its newest in-house models. Bing Image Creator is now powered 100% by the new image model end-to-end, while the new voice model runs twice as fast at 32% lower cost. The releases mark a major push by Microsoft AI to run its own tailored models directly across flagship products.
Microsoft just launched MAI-Image-2.6, a new image generation and editing model that pulls real-time web context to ground visual details. It brings granular control over composition and styles for creative workflows, alongside a lighter Flash model that delivers production quality at less than half the price.
Black Forest Labs just launched FLUX 3 into early access, a multimodal foundation model that jointly trains on images, video, and audio using its Self-Flow architecture. It generates up to 20-second video clips complete with synchronized native sound and even adapts to robotic action prediction. Open-weight Dev access and standalone image generation are slated to follow in the coming weeks.
Qwen-Image-3.0 just launched as a third-generation foundational image generation model designed for genuine utility. It handles 4.5k token prompts for complex layouts like storyboards and newspapers, renders 10px text in 12 languages, simulates web pages and games, and retrieves real-time web knowledge.
ABot-World just open-sourced a real-time world simulator that lets you continuously explore and steer an AI-generated environment with action controls. It runs on a single desktop RTX 5090 GPU, delivering 720p video at 16 FPS with 1.2-second latency. Basically, instead of short video clips, you get an endlessly unfolding world running entirely on local consumer hardware.
Microsoft just released Mage Flow, an open-source 4B-parameter model that handles both text-to-image generation and instruction-based editing. It features native ControlNet capabilities and multilingual text rendering, while a 4-step Turbo variant spits out 1024px images in under 0.6 seconds on a single A100. At 17.5GB, it brings fast, interactive image manipulation directly to mid-to-high-end GPUs.
Adobe just updated its experimental Project Indigo camera app with an "AI Playground" suite, adding generative filters, object removal, and photo reshoot feedback. Surprisingly, the tool currently leans on Google's Nano Banana model rather than Adobe's own Firefly. It is rolling out to a small group of users as a test with an opt-out toggle.
Runway just launched Agent 2.0, turning simple text prompts into complete marketing briefs and multi-platform campaign assets. It can ingest performance data from platforms like Meta and YouTube, then orchestrate models like Gen-4.5 to output auto-formatted variants for different markets. Why it matters: Runway is making a serious play for end-to-end marketing workflows, moving far beyond standalone video generation.
Roblox just unveiled Build, a mobile-first AI creation tab inside its app that lets anyone generate playable 3D games directly from plain text prompts without writing code. The tool automates mechanics, environments, characters, and audio using proprietary 3D gaming models. It launches a free public alpha in New Zealand on July 28, with professional testing and analytics agents coming to Studio soon.
Google just brought text-to-image generation directly into Search AI Overviews to mark Google Images' 25th anniversary. Powered by its latest Nano Banana model, the tool turns text prompts into custom visuals alongside a newly redesigned personalized browse gallery. Both features roll out in English over the coming weeks.
Researchers just introduced Motion4Motion, a training-free framework that transfers video motion between completely different characters without relying on predefined skeletons or ControlNet. Instead of rigid bone rigs, it tracks dense pixel motion flows and maps them during inference. This lets you map movements between wildly different shapes, like transferring a fox's leap onto a giraffe.
Alibaba open-sourced Wan-Animate-2, an end-to-end character animation model that animates still photos using driving videos. It replicates body movements, delicate finger gestures, and facial expressions—even on non-human characters and multi-person scenes—while supporting camera viewpoint controls.
Meta just pulled the plug on a new Instagram AI feature that let users generate images referencing public accounts simply by @-mentioning them. Following immediate backlash from SAG-AFTRA and child safety advocates warning of likeness theft and sextortion, Meta admitted the tool missed the mark and shut it down completely.
Open-source matting model Lucida just launched to fix where typical removers fail, cleanly isolating semi-transparent glass, camouflage, drop shadows, and fine hair. At under 900MB on an MIT license, it runs locally on consumer GPUs and beats commercial baselines across several edge cases.
Nvidia just updated its open-source PID decoder to version 1.5, bringing sharper detail and cleaner color fidelity without grid artifacts. It turns 512×512 latents straight into 2K or 4K renders on consumer GPUs in mere seconds. Why it matters: it bypasses slow, two-step upscaling workflows and works out of the box with models like FLUX and Qwen-Image.
Reve just launched Reve 2.1, its native 4K image model that recaptured the No. 2 spot on Arena behind GPT Image 2. The update outputs full 16-megapixel renders with complex layout planning and foreign-text rendering, all while training on less than a tenth of rivals' compute. It proves independent labs can still punch way above their weight against tech giants.
ByteDance just launched Seedream 5.0 Pro, an image model tailored for real design workflows instead of random generation. It tackles high-density infographics with complex typography, separates elements into layers, and executes edits based on spatial sketches and handwritten annotations. It basically turns image generation into a controllable creative collaborator.
Ant Group's Robbyant just open-sourced LingBot-World 2.0, an interactive world model that streams real-time 720p video at 60 fps. It pairs a causal pretraining approach with dual pilot-and-director agents to handle character actions and dynamic scene building over extended interactions. Weights for 1.3B and 14B models are up on Hugging Face.
Meta just rolled out Muse Image, its first image generation model from Meta Superintelligence Labs, natively inside Meta AI. The model lets users turn prompts into graphics, cleanly edit specific areas by circling them directly on the canvas, and redesign living spaces with real web products. It's free for everyday use, though an @-mention referencing feature was quietly scrapped following user backlash.
