Runway Aleph can precisely alter specific parts of a video, all while maintaining the integrity of everything else. Change outfits, hairstyles, lighting, locations and much more. All you need to do is tell Aleph what you want.

With Eleven Music, you can start with a single prompt, then edit and fine-tune each section of your track until it's just right. In this video, Juliette (Music Partnerships) walks through prompting strategies and techniques for creating a high-quality track.

Realtime interactive generative models FTW! Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM! * Live Jamming with audio input 🎤🎸🎵 * Personalize your own models 🔧 * Tech report 📜 Links below in the 🧵...

(1/2) Filmmakers, it's time to #FindYourFlow. This week, we’re talking about lighting.💡 You can use light to create mood, draw the eye, and tell a better story. This isn't just about brightening things up; it's about creating an atmosphere. Looking for ways to describe

Runway Aleph has granular object control. Which means you can add to or alter your video in ways which feel both natural and realistic without any complex prompting or key framing. Or, you can break the laws of physics altogether. All you need to do is tell Aleph what you want.

This model is only 💾2.7MB (or 2.1MB SOG compressed!) and plays supremely well to the strengths of gaussian splats. The soft, spiky, fluffy stuff has been perfectly captured during training. It would be challenging to replicate this using traditional polygon modelling.

Suno Studio is coming... Multi-track creation. Export to MIDI. And much more. Join the waitlist now suno.com/studio-waitlist

AI is getting crazier. Pika’s new AI model creates some of the most realistic lip sync videos yet. Perfect lip-sync. Full-body motion. Any length you want. Ready in 6 seconds or less, in HD... 6 insane examples:

Interesting research turning WiFi signals into 3D human pose maps. No cameras, just routers tracking body position through signal reflections. Paper: DensePose From WiFi Read here: arxiv .org/pdf/2301.00250

Matrix-Game 2.0 — The FIRST open-source, real-time, long-sequence interactive world model Last week, DeepMind's Genie 3 shook the AI world with real-time interactive world models. But... it wasn't open-sourced. Today, Matrix-Game 2.0 changed the game. 🚀 25FPS. Minutes-long

Your latest limited-time free Fab assets have dropped! ✨ Get a detailed Warehouse Environment, a ferocious "Werewolf" with a zombie skin bonus, and the powerful Magic Spline Plugin to bring your project levels to life. Get them all before August 26th! 👉

📣Matrix-3D: Omnidirectional Explorable 3D World Generation📣 Matrix-3D is a 3D world model which generates large-scale explorable 3D scenes from a single image or text prompt, with SOTA performance. - Project: matrix-3d.github.io - Code: github.com/SkyworkAI/Matr…

We’ve made our Startup Grants program even better. We’ve extended the program from 3 to 12 months and it now includes over 680 hours of Conversational AI, for free. Plus high concurrency limits and improved support.

Vibe Minecraft: a multi-player, self-consistent, real-time world model that allows building anything and conjuring any objects. The function of tools and even the game mechanics itself can be programmed by natural language, such as "chrono-pickaxe: revert any block to a previous

Community spotlight! jtydhr88 brought OpenCut into ComfyUI 🎉 OpenCut lets you trim, cut, and arrange video clips easily in your browser — 100% locally. With this extension, you can enjoy this entire experience inside ComfyUI!

[1/N] 🎥 We've made available a powerful spatial AI tool named ViPE: Video Pose Engine, to recover camera motion, intrinsics, and dense metric depth from casual videos! Running at 3–5 FPS, ViPE handles cinematic shots, dashcams, and even 360° panoramas. 🔗 research.nvidia.com/labs/toronto-a…

Tencent presents Yan: Foundational Interactive Video Generation. It has been only two months since our release of Self-Forcing, and there are already two world foundation models built on top of it. Chinese teams are building at the speed of light! greatx3.github.io/Yan/

Introducing Higgsfield Draw-to-Video. RIP Prompts. Turn your sketch into an absolute cinema. Works with all our video models: MiniMax, Veo 3 & Seedance Pro. This is possible ONLY in Higgsfield. Retweet to unlock the full capacity of the best video models in your DMs.

Higgsfield just ended prompt engineering. Forever. They unlocked the full power of the “best” video models and made them obey one simple rule: draw on an image → it moves. No prompts, no limits, just pure creative control. Higgsfield AI 🧩

Imagen 4 is now generally available! The update also introduces a new Imagen 4 Fast model, for rapidly generating images at only $0.02 per image.