Image created with Gemini. Image prompt: A 1983 Russell Mulcahy music video still of an ornate brass film projector at the top of a Victorian Gothic staircase casting a blinding white beam through heavy fog, the beam eclipsed mid-air by a black disc with a molten gold corona ring, an anonymous adult woman in a flowing luminous white dress with wind-blown teased hair standing arms-outstretched in the beam, slow-motion dove crossing the corona, doors bursting open with white backlight, blue-black shadows and cold silver-blue moonlight, 35mm grain with bloom and halation, large bold chrome serif title card reading VIDEO glowing at the top of the frame, 16:9.
Introducing Muse Image and Muse Video, the first media generation models developed by Meta Superintelligence Labs. Muse Image is our most advanced image generation model yet. It follows instructions faithfully, edits with precision, composes from multiple references, and draws”
https://x.com/AIatMeta/status/2074577662840832382
Meta Muse Video just entered the Video Arena at #3. @AIatMeta’s new video model scored 1459 in the Text-to-Video Arena. It outperforms Alibaba’s HappyHorse 1.0 by +30pts and ranks ahead of Grok Imagine, Sora 2 Pro and Google Veo-3.1 models. Meta has now reached the video AI”
https://x.com/arena/status/2074591193783320851
Today, we’re introducing SimFoundry, our real2sim2real framework at NVIDIA GEAR that automatically turns real-world scenes into simulation-ready worlds from a single image or video. Website:
https://t.co/Iw38VtarSA Paper:
https://t.co/GcDYAUfVwP This work marks a major step for”
https://x.com/yukez/status/2072697990402170906
I have been playing these world models/games since the first diffusion DOOM, and multiplayer at 20 FPS is pretty neat. “A dream of rocket league,” indeed.”
https://x.com/emollick/status/2074348274136346871
MIRA – Blog post
https://mira-wm.com/blog-post/
Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other”
https://x.com/gen_intuition/status/2074104524596457706
Yeah this is cool! Get the ads-b track of the actual helicopter → line up timing with cable news footage → estimate camera field of view to match the 3d view with the real footage. And volia a 3d recreation!”
https://x.com/bilawalsidhu/status/2072857221147324418
1/ today, with the launch of muse image and the preview of muse video, we wanted to share more samples from the model alongside research details and eval results see some more samples from muse video below (and see thread for research blog!)”
https://x.com/alexandr_wang/status/2074579670712934428
Quick test w/ Seedance. Video-to-video AI models are getting really good.”
https://x.com/bilawalsidhu/status/2074193958549275040
Create videos in seconds with Google Photos’ Video Remix
https://blog.google/products-and-platforms/products/photos/video-remix/
Introducing Muse Image and Muse Video
https://ai.meta.com/blog/introducing-muse-image-muse-video-msl/
Meta launches Muse Image for AI image generation in its apps
https://www.testingcatalog.com/meta-launches-muse-image-across-its-apps-and-previews-muse-video/
what a good video”
https://x.com/sama/status/2075068286107316317
This is IronSight – a 4D reconstruction built by fusing footage from two pairs of meta ray-bans. A google research buddy saw the prototype and joked this would’ve been a siggraph paper a few years ago. Today it’s a weekend build with fable. Stay tuned for more mad science. Happy”
https://x.com/bilawalsidhu/status/2073248618144837848
I often use Pinokio to download and work with local open source AI tools/models, and one neat thing is that it exposes them seamlessly to Code and Codex. GPT-5.6 actually found my local video models and image models and used them as a cheap alterative to paid APIs at one point.”
https://x.com/emollick/status/2074930119173460007
Fable: “Last and First Men is out of copyright. I want you to make a movie that features a reading of it with appropriate mixes of animation and images using access to the APIs you have (elevenlabs, hugging face) . Give me the first 10-15 minutes, ending at an appropriate break.
https://x.com/emollick/status/2072872373758382497
LingBot-World 2.0 (Infinity) is out on Hugging Face interactive world model with: Hour-long generation with zero quality drift Rich actions & events: attack, cast spells, shoot, summon storms Agentic world: a Director Agent drives real-time world evolution 720p/60fps.”
https://x.com/_akhaliq/status/2074936755296641520
Four people just played a full 2v2 Rocket League match inside a neural network. Every frame they saw came out of a 5B-parameter model dreaming the whole game, 20 frames a second, on a single Nvidia B200, with “no physics engine, no rendering engine, and no explicit 3D”
https://x.com/TheRundownAI/status/2074184559768277398
RynnWorld-4D 4D Embodied World Models for Robotic Manipulation”
https://x.com/_akhaliq/status/2074927532688695436
LingBot World 2 — Reactor
https://www.reactor.inc/lingbot-world-2
Okay this live demo is zippy af — give it a try! I’m gonna have to vibe code some dopeness with all these world model APIs dropping left and right.”
https://x.com/bilawalsidhu/status/2074940598604226602
Wow. These cats use an AI video model to generate a fake video of a cube copying the motion of the pixel you wanna track, then use classical techniques to extract the full 3D pose. Insane how well it works.”
https://x.com/bilawalsidhu/status/2075109483798307170
It’s really good — feels like the moment where the voice modality for AI apps will finally take off. Upgrade to the latest version of the ChatGPT App to get it. (Also great launch video.)”
https://x.com/collision/status/2075183069137633587
ByteDance set to launch Seedance 2.5 with 3-minute output
https://www.testingcatalog.com/bytedance-set-to-launch-seedance-2-5-with-3-minute-ai-video-output/
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model
https://research.nvidia.com/labs/genair/flex-forcing/
This is a video from our all-hands, it’s a rare look behind the scenes of the early bringup of F.03 F.01, F.02, and F.03 were all designed and walking within a year of each other. The pace of progress is mind-blowing, especially considering each robot was a new architecture,”
https://x.com/adcock_brett/status/2075234184164196580
Introducing Video Remix in @GooglePhotos. 📹 Powered by our Gemini Omni model, it lets you reimagine your videos in new styles with a library of easy-to-use templates. To get started, simply select Video Remix in the Create tab. You’ll be able to instantly apply cinematic”
https://x.com/Google/status/2074958687983010116
LingBot-Video is out on Hugging Face MoE-based video foundation model built for embodied intelligence 30B params, only 3B active at inference Augmented with 70K hours of embodied data on top of large-scale internet video pretraining”
https://x.com/_akhaliq/status/2074932729376870826
You may remember the first image of a black hole that computational astrophysicist Chi-kwan Chan helped capture. Now he’s working toward something no one has made before: the first video of one.
https://x.com/OpenAINewsroom/status/2074646823990669445
We are excited to launch muse Image, the first media generation model built by MSL. Muse image can use reasoning, refinement, and tools to improve precision and quality, with very clear test time scaling trends. Also sharing Muse Video preview today.
https://x.com/shengjia_zhao/status/2074577897009152298
Ohhh, hang on. A few things at once! First, the newly dropped Meta Muse spark 1.1 is.. their smallest model from MSL! Second, it’s natively multi-modal with video understanding and 1M tokens in context window! Third, they are opening up an API for it! It’s waitlisted but”
https://x.com/altryne/status/2075237837033889911
we are truly just getting started on video 🙂 look forward to sharing more!”
https://x.com/alexandr_wang/status/2074687661428572403
This looks like another step toward removing the data bottleneck in robotics. The bottleneck exists because recording demonstrations is easy, but labeling every grasp, hold, move, and release is slow and expensive. Perceptron Egocentric dropped a new robotics video annotation”
https://x.com/rohanpaul_ai/status/2075286203583398181
Hiring a producer and video editor for my channels (2.1M+ subscribers interested in the frontier of creation & computing). Help turn complex topics and mad science experiments into videos that hit. Part-time or full-time. Remote welcome. Apply here:”
https://x.com/bilawalsidhu/status/2075052559820075416
Leave a Reply