Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: Wide cinematic shot of a futuristic orbital command center with thousands of small holographic image panels floating in a precise tactical grid, each showing different AI-generated scenes, cool blue and green lighting, deep space visible through vast windows, high contrast rim lighting, sleek military sci-fi aesthetic, dramatic sense of scale and control
Our View on Agentic AI: AI Assistants That Work For You, In Your Favorite Apps | Adobe Blog https://blog.adobe.com/en/publish/2025/10/28/our-view-agentic-ai-assistants-that-work-you-in-your-favorite-apps
One of the coolest 3d real estate demos I’ve seen in a while. Treedis brings together gaussian splats for area understanding → BIM data to check which units are available → Matterport for indoor views → and image editing AI to restyle decor and see different times of day. The https://x.com/bilawalsidhu/status/1988328067140644953
After a year of team work, we’re thrilled to introduce Depth Anything 3 (DA3)! 🚀 Aiming for human-like spatial perception, DA3 extends monocular depth estimation to any-view scenarios, including single images, multi-view images, and video. In pursuit of minimal modeling, DA3 https://x.com/bingyikang/status/1989358267668336841
Paper page – Depth Anything 3: Recovering the Visual Space from Any Views https://huggingface.co/papers/2511.10647
Depth Anything 3 Recovering the Visual Space from Any Views https://x.com/_akhaliq/status/1989336687529619858
Depth Anything 3 – a Hugging Face Space by depth-anything
https://huggingface.co/spaces/depth-anything/depth-anything-3
I genuinely think we’re on the cusp of a new type of creation engine. Feels less like prompting and more like puppeteering reality itself. MotionStream is a taste of what’s to come: https://x.com/bilawalsidhu/status/1986877076839014462
MotionStream: Real-Time Video Generation with Interactive Motion Controls
https://joonghyuk.com/motionstream-web/
Wildminder on X: “MotionStream: Real-time, interactive video generation with mouse-based motion control; runs at 29 FPS with 0.4s latency on one H100; uses point tracks to control object/camera motion and enables real-time video editing. https://t.co/fFi9iB9ty7 https://t.co/zKb9u3bj9g” / X
https://x.com/wildmindai/status/1985828041566941576
Google is now using Gemini to cross-reference ~250M places with Street View imagery to identify visible landmarks for turn-by-turn nav. Think iconic buildings, gas stations and restaurants. So instead of “”turn right in 500 feet”” you get “”turn right after the Thai Siam https://x.com/bilawalsidhu/status/1986525085398941974
Adobe and Google Cloud Expand Strategic Partnership to Advance the Future of Creative AI https://news.adobe.com/news/2025/10/adobe-max-2025-google-cloud
Early look at images generated by Nano Banana 2 via Media AI https://www.testingcatalog.com/early-look-at-images-generated-by-nano-banana-2/
Exclusive: New leaked image samples by Nano Banana 2 https://www.testingcatalog.com/exclusive-new-leaked-image-samples-by-nano-banana-2/
Excited to share our latest @SophontAI release 🥳 “”How to Train a State-of-the-Art Pathology Foundation Model with $1.6k”” We present OpenMidnight, our first pathology foundation model! It has SOTA perf. despite being only trained on 12k whole slide images w/ $1.6k compute! https://x.com/iScienceLuvr/status/1989390268316221861
We’ve been integrating Isaac across the industry and have realized developers are missing a single platform for Physical AI – prompt engineering, deployment, and integration. Today we are excited to release Perceptron’s Platform – supporting our API – supporting chat”” / X https://x.com/AkshatS07/status/1988713765152649711
Perceptron AI on X: “Perceptron’s platform is here — built for Physical AI Developers can now use Isaac-0.1 or Qwen3VL 235B via: Perceptron API — fast, reliable multimodal intelligence Python SDK — simple, grounded prompting for vision + language Build apps that see and understand the world. https://t.co/5ZyaOGQb1i” / X
https://x.com/perceptroninc/status/1988713482460750290
Disney+ to Allow User-Generated Content Via AI https://www.hollywoodreporter.com/business/digital/disney-plus-gen-ai-user-generated-content-1236426135/
We are just scratching the surface of precise control over AI video generation. MotionStream unlocks real-time video with interactive motion controls. You can interactively generate video based on motion inputs (like drawn trajectories, camera movements, or motion transfer). https://x.com/bilawalsidhu/status/1986838921712701833
@giffmana A joint isotropic gaussian has the property that marginals along all projections are also gaussian (and vice versa). Not true of Laplace.”” / X https://x.com/ylecun/status/1988999683801510063
You can just bike around your city with a camera and auto identify vacant & derelict buildings. Ireland has a housing crisis. Thousands of empty buildings. Nobody knows where they all are. UCD’s Spatial Dynamics Lab is using the latest in AI to map them automatically — https://x.com/bilawalsidhu/status/1987238945739186444
Safer (and Sexier) Chatbots, Better Images Through Reasoning, The Dawn of Industrial AI, and more… https://www.deeplearning.ai/the-batch/issue-327/
This week, we introduced new AI updates to @GooglePhotos that make it even easier to edit, create and search. Here are four new features to try. https://x.com/Google/status/1989468389480501458
Our November Pixel Drop is here and full of time-saving tools, enhanced security and extra personalization, including: 🍌 Remix any photo with Nano Banana, our Gemini image generation and editing model, right in Messages ✨ Find details faster with AI-powered notification”” / X https://x.com/Google/status/1988377964686266518
Today, Photoroom is turning 6, we’re releasing our second text-to-image model from scratch– and open-sourcing not only the weights, but also the full process. Photoroom, from day 1, was successful thanks to open source in the early days and it’s our way to give back to the https://x.com/matthieurouif/status/1988981733866271223
Nano Banana can be prompt engineered for extremely nuanced AI image generation | Max Woolf’s Blog https://minimaxir.com/2025/11/nano-banana-prompts/
I don’t find this mind-blowing tbh. Nano-Banana is a general purpose LLM similar to 2.5 Flash that also has the capability to produce highly structured images grounded on its outputs; this isn’t zero-shot diffusing maths. Probably built not unlike Hunyuan Image 3. https://x.com/teortaxesTex/status/1988390269998559584
QwenEdit-2509 Photo2Anime: LoRA transforms photos into anime; delivers better results than prompting for “”anime”” without it. https://x.com/wildmindai/status/1988309389259010112
Qwen Image Edit Light Restoration app Easily remove shadows and relight in seconds. Here’s how + 4 wild examples:👇 https://x.com/minchoi/status/1988008926797787208
Leave a Reply