Ideogram just launched Character, a new feature and API that generates consistent AI characters from a single reference image across different poses, outfits, and scenes. In testing, it locked facial identity where rivals drifted, making it a huge win for storybook creators and branded avatars.
Adobe just added Generative Upscale to Photoshop, letting users boost image resolution up to eight megapixels with a single click without losing clarity. The update also introduces Harmonize to automatically match lighting across composite elements, alongside an upgraded Remove Tool and a Firefly model picker.
Tencent Hunyuan just open-sourced Hunyuan3D World Model 1.0, an industry-first model that turns a single prompt or image into an explorable, interactive 3D scene. It connects directly with standard CG pipelines for editing and simulation, built to speed up game dev and VR creation.
Meshy just launched Meshy 5 Preview, bringing sharper geometry, multi-view image alignment, and a library of over 500 new animations for rigged characters. It also adds a smart AI prompt helper to make asset creation faster. Why it matters: It significantly cuts down manual cleanup and rigging, pushing AI 3D assets closer to ready-to-use production pipelines.
Midjourney just added custom start and end frame support to its AI video features, letting creators morph between two distinct images or produce seamless loops. The video workflow is now directly accessible inside the Discord bot as well, though the web interface remains the recommended experience.
Microsoft is experimenting with a new Copilot 3D feature that generates 3D objects from uploaded images. Testers can now duplicate and manage their assets inside a new My Creations hub. The fidelity is still visibly rough, but it signals Microsoft's push to bring quick 3D prototyping directly into its AI assistant.
Higgsfield AI just launched Steal, a browser extension that lets users hover over any web image to capture its pose, lighting, and outfit, recreating it with their own face using Soul ID. While it turns visual cloning into a one-click affair, the tool is already drawing heavy backlash over creator copyright theft and the security risks of side-loading unverified extensions.
Google just added new creation tools to Google Photos, letting users animate static gallery pictures into six-second video clips with a single tap. The update also introduces Remix to transform photos into anime or 3D animation styles, with SynthID digital watermarks applied to all outputs. Why it matters: It turns your personal camera roll from a passive archive into an interactive creative canvas.
DeepMind and academic researchers just unveiled Aeneas, a multimodal generative neural network built to contextualize, restore, and date damaged Latin inscriptions. It handles missing text of unknown length and narrows down dates to within 13 years. Pairing historians with the AI boosted confidence by 44%, beating both human experts and AI operating alone.
Google just introduced conversational image segmentation for Gemini 2.5. Instead of relying on single nouns, the model parses relational instructions like "the car farthest away" or abstract ideas like weather damage to return pixel-level masks via a single API call.
DuckDuckGo just rolled out a new toggle that lets you hide AI-generated images from search results. Powered by open-source blocklists from uBlockOrigin and uBlacklist, the filter won't catch everything, but it drastically cuts down on AI slop so you can actually find real photos.
Apple just introduced Emoji Game for Apple News+ subscribers in the U.S. and Canada, turning casual icons into a daily brainteaser. Players use a curated set of emoji — including Genmoji created via Apple Intelligence — to fill in phrase blanks using as few moves as possible. It is a subtle way for Apple to weave its generative AI tools directly into daily casual habits.
Midjourney just announced it is investigating opening up an Enterprise API so companies can integrate its image generation tools into their own services. The team has shared an application form to figure out what features businesses actually need and gather interest for upcoming updates.
Runway just introduced Act-Two, its next-gen motion capture model that tracks head, face, body, and hands using just a driving performance video and reference character. It brings major quality bumps, though it's currently limited to enterprise clients and creative partners.
Exists just opened its generative AI platform to the public, letting anyone build functional 3D worlds from text prompts without code or 3D modeling skills. Instead of flat video diffusion, it runs on a custom cloud fork of Unreal Engine, delivering playable spaces with lighting, AI bots, and multiplayer support out of the box.
Black Forest Labs just launched Kontext Komposer and Kontext-powered presets, letting users transform images without typing a single prompt. It handles background swaps, headshot relighting, and product placements. The tool is currently available for free in their playground.
Dynamicslab just launched Mirage, a game engine that scraps pre-built maps and static assets entirely. Powered by a hybrid transformer-diffusion model running in the cloud, it renders interactive 3D environments frame-by-frame based on player movements and prompts. While currently streaming at around 16 fps, it offers a wild peek into unscripted gaming.
NVIDIA just rolled out TensorRT optimizations for Black Forest Labs' FLUX.1 Kontext [dev] model, bringing over 2x faster image generation and editing to RTX GPUs. Quantization cuts model size down to 12GB for FP8 and 7GB for FP4, allowing creators to run step-by-step visual edits locally without complex workflows.
Baidu just open-sourced its ERNIE 4.5 model collection on Hugging Face, spanning lightweight text models to massive multimodal models reaching 424B parameters. The release provides checkpoints in both PyTorch and PaddlePaddle alongside dedicated Thinking variants, giving open-source developers a serious heavyweight alternative.
Meta is testing an opt-in cloud processing feature on Facebook that scans unpublished photos from users' camera rolls to generate AI restyles and recaps. While Meta insists these personal images aren't currently used to train models, it refused to rule out doing so down the road.
