Introducing Gen-3 Alpha: Runway’s new base model for video generation. Gen-3 Alpha can create highly detailed videos with complex scene changes, a wide range of cinematic choices, and detailed art directions. runwayml.com/gen-3-alpha (1/10)

Thread on unexplored things Gen-3 Alpha can do with text

Woah what??? Microsoft just dropped Florence-2 on Hugging Face with an MIT license!! Pretty huge. Florence was initially Microsoft’s internal CLIP model, and they now expanded it to do various tasks like captioning, object detection, OCR, … just by prompting the model

Atomium under construction for the Brussels World's Fair 'Expo 58' as captured by Dolf Kruger in 1957

Built something new -> startuproaster.com This is a little weekend project I did for fun. Wanted to try AI and chat interfaces. It was fun to build (and use!) You can it yourself for free to ROAST your startup ideas and maybe even get inspiration. Give it a try and let

Contender for favorite chart of all time: Predictions vs. Reality for solar energy.

New Three.js-based video editor! 🙌

🎉 TinyBase v5.0 🎉 We are thrilled to unveil this major new release - "The One You Can Sync" - and a whole load of exciting new local-first opportunities as a result. CRDTs for the rest of us 😎

StartupRoaster is now live on PH. Let me know where I messed up: producthunt.com/posts/startupr…

New: Disney research breaks down the design of their iconic robot. 🤖 This is the blueprint for designing robots with personality. It combines the best of - – Legged robot control – Learning-based control – Character animation The output: a friendly robot that can create

Today we are releasing Gen-3 Alpha Image to Video. This update allows you to use any image as the first frame of your video generation, either on its own or with a text prompt for additional guidance. Image to Video is major update that greatly improves the artistic control and

Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time, promptable object segmentation in images & videos. SAM 2 is available today under Apache 2.0 so that anyone can use it to build their own experiences Details ➡️ go.fb.me/p749s5

Combine live action with Generative Visual Effects. Learn how with Gen-3 Alpha: academy.runwayml.com/gen3-alpha/usi…

📝 New Blog Post 📝 In this article, I share everything I learned to recreate a custom "Retro" style post-processing effect 📺 From dithering to replicating a CRT, I detail the many shader techniques that will elevate your next React Three Fiber project blog.maximeheckel.com/posts/the-art-…

What can an 8-year-old build in 45 minutes with the assistance of AI? My daughter has been learning to code with Cursor and it's mind-blowing🤯 Here are highlights from her second coding session. In 45 minutes she built a chatbot powered by Cloudflare Developers Workers AI 👀

2 years, YC, 5 team members, and 2000 commits later: Instant is now open source!

Two years ago, a single wind energy project in Germany with just three turbines required 36,000 pages of documentation. Then they passed permitting reform to cut red tape. Now Germany is a leader in clean energy deployment. Some lessons here for the United States...

Robotics datasets take up a lot of space, especially images (which are often stored in raw format or at best jpeg). Many teams naturally consider switching to video codecs such as h.264, but the question naturally arises how this will affect their trading pipeline. Check out

The performance boost in the WebGPURenderer from r167 to r168 is truly amazing! I can't wait for the day when developers embrace WebGPURenderer purely for the speed gains delivered by render bundles, UBOs as a first-class API, occlusion queries, compute, and so much more!

Shooting visual effects with a disposable camera and Gen-3 Alpha.