Juliana Loh

STUDIO GHIBLI JUST HANDED YOU THEIR ANIMATION SOFTWARE. The studio behind Spirited Away, My Neighbor Totoro, and Princess Mononoke built their films on a tool called Toonz. In 2016 they open-sourced it. It now sits on GitHub, completely free, and most animators have no idea. It's called OpenToonz. This is not a stripped-down "community edition." It's the actual production software, with Ghibli's own custom modifications folded directly into the public release. The same toolset that drew some of the most beloved films in cinema history is a free download on your machine right now. → Hand-drawn frame-by-frame animation with onion skinning → Vector and raster drawing in the same workflow → The GTS scanning tool Ghibli built for digitizing hand-drawn art → Node-based effects, compositing, and color tools → Skeleton rigging for cut-out and puppet animation → Frame-by-frame motion tracking → A scripting console for automating repetitive tasks → Runs on Windows and macOS Toon Boom Harmony, the industry-standard alternative, costs up to $1,575 per year. Adobe Animate is $263 a year, forever, and you never own it. Both stop opening the day you stop paying. OpenToonz costs $0. You own it. It works offline. It never expires. And it has a feature set built by a studio that won an Academy Award. Every aspiring animator believes the barrier to entry is expensive software. That belief is the only thing the paid tools are actually selling. Ghibli quietly removed that barrier nine years ago. The whole thing is open source. Clone it, build it, or download the installer and start drawing today. 100% free. 100% open source. BSD-3 License.

@abxxai Nice

What AI is doing right now is insane.🤯 ChatGPT Image 2 turns your ideas into full storyboards with cast and scenes… then Seedance 2 turns those into full cinematic shots. Exact prompts below 👇

I painted my entry for the @VIVERSEofficial created in @openbrushapp contest two weeks ago. Here is the theme. What does home make you feel? I created a ‘ship’ powered by a teddy bear + the experiences we form as it converts to new memories. #hope viverse.com/nvDQbPq

Claude for Excel, PowerPoint, and Word are now generally available, and Claude for Outlook is in public beta. As Claude moves between your Microsoft apps, it carries the full context of your conversation.

SOMEONE JUST KILLED THE REAL ESTATE INDUSTRY A guy scanned an entire house with his phone. Uploaded it. Now anyone on Earth can walk through it in a browser tab. No app. No VR. No agent. No appointment. Click → you’re inside. Every room. Every angle. Every shadow. Photoreal. The numbers are insane: - Agent fee on a $500k home: $15,000 - Cost to make this scan: ~$200 - Time to “tour” 50 houses: one evening - File size: smaller than a TikTok The science is wild too: It’s called 3D Gaussian Splatting instead of polygons (how games render), it uses millions of tiny glowing “splats” of color and depth. AI reconstructs reality from your photos. The result loads on a phone and looks like you’re THERE. The grift opportunity is even wilder: Freelancers are already charging $300–$800 per scan for realtors, Airbnbs, venues, car dealers, museums. One person + one phone + one weekend = a business. Open source. Built on PlayCanvas. Free GitHub: github.com/playcanvas

📣 Today, I’m excited to walk you through Unity’s NEW AI offering, Meta MCP Extensions, and agentic tools to demonstrate how we can 𝗕𝘂𝗶𝗹𝗱 𝗔 𝗙𝘂𝗹𝗹 𝗩𝗥/𝗩𝗥 𝗚𝗮𝗺𝗲 from start to finish using these AI tools in a practical way.  🎥 Full video available at: youtu.be/bWxIF903t_I 📌 Here’s what I’m covering today: - Unity VR project setup (with OpenXR plugins) - Installing the Unity AI Assistant and demos - Configuring Unity MCP + Meta MCP Extensions - Configuring Claude Code & MCPs - Building a VR/MR Basketball Game with the Unity AI Assistant, Claude Agent, and external Claude Code CLI - A lot of iteration with Claude Code + the Meta XR Simulator 💡Also, it’s been a while since I've posted a new video, and I’m genuinely excited to be back, especially with a topic like this that I know many devs have been waiting for.

at @nianticspatial, we're building the real-world model for physical AI. we believe the next generation of AI will move beyond the screen, into real-world environments where some of the hardest problems need to be solved. with high-fidelity gaussian splats as the foundation – robots, AI agents, & autonomous systems can see, localize, understand, & operate in the environments that matter most.

Rethink everything you know about story. Modern Audience Conference is a one-day online event on narrative games, transmedia, AI-era storytelling & modern audiences. Features @Jeff_Gomez Ken @Levine a special @YokoTaro film, and more. Tickets: £14.95 modernaudience.org

I have been to a lot of startup demo days but have never seen such a great writeup as this.

1枚の画像から「顔と髪を分離」した3Dアバターを生成する新手法が登場。 3D Gaussian Splatting（3DGS）を活用し、物理演算（PBD）で髪の自然な揺れを再現します。 従来困難だった髪の独立制御と高精細な表情アニメーションを両立した画期的な技術です。 髪の着せ替えや除去も自由自在に。

Blender live preview on Vision Pro is wild 🤯

FROM MYTHIC FIELD TO SYSTEM: How Storyworlds Actually Scale — Here is more on my newer thinking in terms of entertainment franchise universes. linkedin.com/pulse/from-myt…

Where do you begin when developing a franchise-worthy storyworld? Hint: it is not the medium. Great talk with me on creating new universes. twist-tales.com/what-jeff-gome…

Turns a single image into a world.

STANFORD JUST DROPPED A TOOL THAT LETS YOU ZOOM INTO A 3D WORLD AND GENERATE NEW CONTENT AT EVERY SCALE it's called WonderZoom you give it an image it builds a full 3D scene from it then you zoom into any region → type a prompt → it generates fine-scale detail that actually matches the rest of the world zooming into a ladybug? it renders the texture on its shell zooming into a beach? sand grains, coral, underwater life the geometry stays consistent across every zoom level wonderzoom.github.io no re-optimization needed it uses scale-adaptive gaussian surfels to update the scene in real-time as you go deeper github.com/jin-cao-tma/Wo… this isn't just 3D generation it's multi-scale world building

The founder of Niantic built Google Earth. He has been building this for years. I got a demo. It is stunning. And is the platform that will bring us infinite realities. I call it the Holodeck.

🚨 Someone just built a fully open-source mocap system that works with any camera. It's called FreeMoCap, a markerless 3D tracking system that runs on ordinary webcams. It turns multiple camera feeds into research-grade skeletal data automatically. 100% Open Source.

World Labs just dropped their newest model of Marble, Marble 1.1.

Spectacles Community Challenge #12 is live! 🕶️ Build in Lens Studio, pick a category (New Lens / Update / Open Source), and submit your work – you know the drill 😉 Up to $14,000 in prizes 🤑 Deadline: April 30 ⏳ Details on our website 🔗lenslist.co/spectacles-com…