Tencent just open-sourced Hunyuan3D 2.0, a two-stage foundation system for generating detailed, textured 3D meshes from single images. By decoupling geometry creation via a DiT shape generator from texture baking with a dedicated diffusion model, it can also texture handcrafted meshes, beating previous open and closed-source baselines.
Runway just launched Frames, its new text-to-image generator engineered for high-fidelity, cinematic visuals. Available to Unlimited and Enterprise subscribers, it packs 19 preset styles and lets users seamlessly turn generated stills into video using tools like Gen-3 Alpha Turbo with a single click. Runway is gunning straight for Midjourney's crown.
Krea AI just rolled out a tool that converts flat 2D images into 3D objects within its real-time generator. Users can rotate, reposition, and scale the converted models while the background updates live. Why it matters: it makes complex scene composition and character posing much easier without manual redrawing.
Black Forest Labs just launched the FLUX Pro Finetuning API, allowing creators to customize flagship FLUX Pro models with as few as 1 to 5 reference images. The custom finetunes reliably preserve unique characters or visual styles at up to 4 megapixels and work seamlessly across the full FLUX tool suite.
Researchers just introduced a new framework that scales diffusion models at inference time beyond traditional denoising steps. By pairing automated verifiers with search algorithms to hunt for better noise candidates, dumping more compute into generation now reliably translates into higher image quality.
Freepik just launched an AI-powered tool to remove and replace image backgrounds. Beyond simple solid color swaps, you can generate entirely new AI scenes using Relight technology to match the lighting seamlessly. It is live now on Freepik.
Netflix and Eyeline researchers just introduced "Go with the Flow," a new method that steers motion in video diffusion models without changing model architectures. By warping latent noise using optical flow fields in real time, it enables precise camera moves and object control while keeping frame quality crisp.
Adobe just rolled out Firefly Bulk Create in beta, letting users resize or swap backgrounds across up to 10,000 images at once. The web tool packages Firefly developer APIs into simple "Remove Background" and "Resize" features aimed at marketers. It relies on consumption-based credits, with PSD export coming later.
Stability AI and NVIDIA just rolled out SPAR3D at CES, turning single 2D images into detailed 3D objects in just 0.7 seconds. The architecture pairs a point diffusion model with a triplane transformer, letting creators edit point clouds and rebuild meshes in 0.3 seconds. Weights are open on Hugging Face for RTX AI PCs.
NVIDIA just unveiled its GeForce RTX 50 series GPUs at CES, doubling generative AI performance with FP4 support. The new quantization cuts model memory needs in half, allowing models like FLUX.1 to run locally on under 10GB of VRAM in just five seconds. The flagship RTX 5090 launches January 30.
Midjourney just rolled out Pinterest-inspired moodboards and multi-profile personalization, letting creators train custom aesthetic models directly from curated image collections. Users now only need 40 image ratings to build a profile instead of 200, and can seamlessly switch between distinct named styles for different creative projects.
Google just unveiled Veo 2, a new video model that generates clips up to 4K resolution spanning several minutes while understanding cinematic prompts like lens focal lengths and depth of field. Alongside it, an upgraded Imagen 3 launched globally in ImageFX, also powering a new image-remixing experiment called Whisk. Veo 2 is currently rolling out via a waitlist on VideoFX.
Adobe just released a preview of its Reflection Removal tool inside Camera Raw, aiming to rescue photos ruined by glass reflections. Powered by AI trained on millions of simulated reflection pairs, it separates foreground reflections from background scenes and lets you adjust the effect via a slider. It currently only supports RAW files, with Lightroom rollout coming soon.
lmarena.ai just launched Image Arena, bringing blind side-by-side battles to AI image generation. Users enter a prompt to get two anonymous outputs from models like FLUX, Stable Diffusion, DALL-E, Recraft, and Ideogram, then vote for the winner ahead of an upcoming leaderboard.
Grok just rolled out a faster, sharper version of Grok-2 to everyone on X for free. The upgraded model runs three times faster with better accuracy and multilingual support, while bundling web search, citations, and the Aurora image model. Developers also get updated API endpoints at lower token pricing.
Midjourney just revealed Patchwork, a standalone web-based infinite canvas designed for collaborative storytelling. Powered by at least three LLMs, it lets up to 100 users map out characters, events, and scenes together in real time. It is rolling out as an early research preview for users who link their Discord and Google accounts.
Apple just released iOS 18.2, iPadOS 18.2, and macOS Sequoia 15.2, bringing the next wave of Apple Intelligence. Users can now create Genmoji, generate artwork in Image Playground, and tap into ChatGPT directly through Siri and Writing Tools. It is live now for localized English, with other languages rolling out starting this April.
South Korean startup Spaid just showcased its Geo AI solution powered by the CYLO engine, which converts GIS and satellite imagery into interactive 3D maps. The system monitors regional data like demographics and traffic to detect anomalies, with adoption already underway by telecom providers and Armenia's national land survey.
Researchers at the University of Surrey just open-sourced NitroFusion, an AI model that generates images in near real time as you type using standard consumer hardware. The framework lets users dial between one and four refinement steps, balancing speed and image quality without cloud GPUs or monthly subscription fees.
Manchester City and Puma just launched an AI kit generator powered by DeepObjects, inviting fans to design the club's 2026-2027 third kit. The Puma AI Creator gives users 15 credits to generate virtual jersey concepts and submit up to two entries by December 20th. The winning submission will mark the first AI-generated kit ever worn in an official match.
