Kimi just launched K3.1 Pro, a 3T-class open-weight MoE model packing 2.8T total and 104B active parameters with a 1M-token context window. It handles full-project game coding across Unreal, Unity, and Godot, while cutting finance hallucinations by 65%. The open weights are slated for release on Nov 4, 2026.
Canva just rolled out Canva Craft, its first in-house image generation model built with help from its Leonardo.ai acquisition. Instead of basic pixels, Craft generates up to 2K graphics across 30 aspect ratios trained directly on real layouts, allowing designs to instantly convert into fully editable layers via Canva Magic. It is available to all users now in Dream Lab.
Ideogram just launched Vector 1.0, its first dedicated vector AI model. It allows users to generate clean, fully editable SVG files directly from text prompts or convert existing images into scalable vector graphics featuring smooth gradients and sharp typography. The model is live now on Ideogram's web platform and API.
Bria just launched Fibo 2, an open-weights image generation and editing model that snagged the top spot on Artificial Analysis's image editing leaderboard. It lets you blend up to four reference images using natural language prompts, though the weights remain non-commercial and require an approval form.
Researchers just introduced HiP3R, a hierarchical pose graph framework for long-horizon 3D reconstruction. It aligns video chunks first and then refines frame-by-frame camera poses to kill accumulation drift. Why it matters: it plugs directly into existing pipelines without retraining foundation models, turning lengthy video walks into consistent 3D scenes.
Tencent just open-sourced Hy-Nomas, an interactive world generation model that turns natural language and camera trajectories into 720p virtual environments. By generating short chunks with persistent memory, it keeps scenes consistent for over a minute, and a 9GB distilled version runs locally on a single consumer GPU under Apache 2.0. Why it matters: It brings real-time interactive video down from datacenter clusters to individual creators and robotics researchers.
Google just rolled out a dedicated business hub inside Gemini to help small businesses handle branding, finances, and daily operations. Powered by its Nano Banana 2.1 model, Gemini can lock in brand kits to generate matching promotional assets, turn raw receipts into interactive charts, and sync directly with Shopify and Canva. It basically gives solopreneurs a full marketing and finance team in one tab.
Researchers just open-sourced GaussiAnimate, an animation tool that tackles tricky soft-body deformations in garments and animals. Instead of relying solely on a rigid skeleton, it pairs an inner bone structure for motion with flexible outer surface bones to handle complex bends and folds. Why it matters: It removes one of the biggest bottlenecks in 3D character rigging.
Skyfall AI just introduced SKY-001, a dedicated engineering world model that can turn a 2D image of a machine into disassembled 3D parts with step-by-step CAD drafting instructions. It also generates building floor plans from outlines, operating faster and at lower cost than general frontier models. Why it matters: Heavy engineering is getting purpose-built AI, though access remains waitlist-only for now.
Viggle just introduced JST-2, a physics-native world model that turns text prompts or images into interactive 3D scenes in about one second. It tracks persistent physical tokens across space, allowing generated characters to deform and move naturally without manual rigging. It renders directly in the browser via 3D Gaussian splatting, putting full 3D environment generation within reach for everyone.
OpenAI just briefly exposed three new image models in its API—aurora-red, green, and blue—before quickly pulling them, only for them to surface in blind Arena tests. Early runs show red prioritizing speed while green yields sharper detail, sparking speculation that GPT-Image-3 is around the corner. OpenAI has yet to release documentation or pricing.
OpenMOSS just released MOSS-Image, a lightweight 5-billion-parameter text-to-image model built for consumer GPUs under an Apache 2.0 license. It excels at drawing bounding boxes for precise composition and rendering clean text within scenes, though it currently lacks support for natural language image editing.
Krea just opened the beta for Krea 3, an image editing model that delivers end-to-end 2K edits in under 8 seconds. It matches Nano Banana Pro and GPT Image 2.5 in quality while introducing bounding box control for multi-turn iterative workflows. A full launch with benchmarks lands next week.
Black Forest Labs just open-sourced FLUX 3 Image Klein, a compact 5.6B parameter model delivering native 4K text-to-image and pixel-perfect editing. Thanks to NVIDIA-optimized INT8 weights, it squeezes onto local GPUs with 8GB memory, making high-end local generation fast and accessible.
Researchers just introduced Möbius, a unified motion-language model that generates, captions, completes, and edits 3D human motion within a single framework. By operating directly on continuous frame-level motion without discrete tokenization or pre-trained motion VAEs, it scales up to 1.7B parameters. Why it matters: It bridges the gap between text prompts and production-ready character animation, allowing creators to describe, generate, and fine-tune complex actions in one place.
Researchers just open-sourced InfiniSplat v2, a feed-forward 3D reconstruction model that turns multi-view photos or long driving videos into fully explorable 3D scenes. By decoupling geometry from appearance prediction, it cuts rendering errors and suppresses noisy artifacts. The entire model weighs around 6.6GB and runs locally on consumer GPUs.
Skywork just open-sourced Matrix Game 4.0, an AI world model that generates playable 3D games in real time. Instead of hallucinating everything from scratch, it offloads physics to a traditional game engine and uses AI to rerender low-poly frames at up to 83 fps on a single consumer GPU, complete with an agent that edits gameplay code on the fly. Why it matters: it solves the visual warping that plagued earlier AI games, proving hybrid neural rendering actually works.
Nvidia just open-sourced Stream Render H3, a real-time diffusion system built on MiniMax H3 that replaces traditional game rendering. The engine only tracks physics and outputs flat semantic maps, while the AI generates textures, lighting, and customizable visual styles. Catch is, running it live takes 8 enterprise GP200 GPUs and over 200GB of storage.
Researchers just open-sourced UniForge 3D, a framework that generates complete 3D assets from just a handful of unposed photos. By pairing visible-surface reconstruction with generative shape completion in a shared anchor space, it fills in unseen angles while keeping fine details sharp.
Researchers just open-sourced Pure, a 3D reconstruction model that transforms ordinary video footage into interactive dynamic 3D environments. Instead of relying on expensive 3D annotations, it post-trains on regular video by extracting monocular depth and motion cues. Clocking in at just 13.2GB with training scripts included, it makes dynamic 3D mapping practical on local machines.
