Introducing Idol Max and Idol Max Turbo, new image-to-3D models built and optimized in-house by fal on top of Idol.
-One image in, a game-ready 3D asset out
-A real mesh in GLB, not a Gaussian splat
-UVs and 2K textures
-Optional PBR materials and auto-rig
Starting today, Gemini 4 Neon is available to Google AI Pro and Ultra subscribers on mobile, desktop, and web.
This new model excels at work that requires frontier-level reasoning and fast responses. 🧵
Introducing AIR-O, a model that decodes what a person is attending to directly from brain scans.
Using only noninvasive brain data, we can generate an image from scratch in real time that depicts where a person is focusing their attention.
This is the first of a new generation of algorithms that can read the shape of thoughts directly from brain activity.
Seedance 5.5 is a great model
With a pass through color / post on these images, they've be very useable in my opinion.
Just raw text-2-image testing which I love doing with new models
🚨 MUSE FEATURE ALERT 🚨
you can now try on clothes in muse before you buy them 👕 👗 👖
muse will offer to show you how you look in something while you’re shopping for it. trying things on in person? as if....
The Google AI Edge Gallery team built a 100% offline language learning app with Antigravity. They combined ASR, Gemma 4, and TTS SDKs, used Figma MCP to map designs to real code, and started it all with a drawing on paper. Watch how they went from idea to working app.
this is actually so good
Eleven v4 + Avatar 6 = 400k views
turning your tts directly into the footage you need in 2 clicks is actually incredible.
people are always asking me how we use ElevenCreative internally at ElevenLabs.
and this is one of the very simple yet powerful combos you can in the same tab.
we've already made a few videos with this workflow on YouTube, and one of them has over 400k longform views.
New trailer for Luca Guadagnino's ‘ARTIFICIAL’, starring Andrew Garfield as Sam Altman.
The film follows the story involving OpenAI focused on the firing & rehiring of CEO Sam Altman.
In theaters on January 8.
Today, we’re excited to share Enact, a research preview of scenes that respond to you.
Enact represents a new way of making AI video, one that’s designed to mimic the experience of directing on set. Built on Pika H3 Flex, it allows a creator to interact with “actors,” manually re-stage a scene, and manipulate the camera—all in real time.
We think this is the beginning of a new paradigm for creation. Read more and reach out for a demo below.
Stop using image models to make images.
Our animators used a video model to make a movie poster.
In our test, GPT Image 2.6 and Nano Banana Pro changed the character’s look in all 20 takes. Seedance 2.5 kept it in 10/10.
Here’s how we did it 🧵
S-Tier Ranking Videos were one of the hottest formats in 2026.
This is the exact formula for building them in a way that rips consistently.
Comment "formats" and I'll send you a database of the top 20 formats for educational content
Proud to announce:
SignalBurn RP is now in Open Beta. A free multiplayer roleplay server inside Cyberpunk 2077 on PC. Make a character, create a legend. Stream it. Clip it. Tell us what breaks. Needs your own copy of the game (2.5). No DLC needed.
https://t.co/ndzWyQ2iyx
Fable 5.2 made a fictitious streamer who browses https://t.co/jSbPcMSYbM, picks a real game, and plays it while reacting to his chat.
Game: Greed II by markmehere (MIT code, CC0 assets)
GPT-6.2 Astra just launched, bringing powerful new capabilities to game development.
Paired with fal, you can sculpt intricate 3D models, render immersive environments in real time, and bring entire game worlds to life.
See what you can build with GPT-6.2 Astra and fal.