#视频

Introducing Atlas: The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.

Today, we are introducing Orbis 1.0, our first Live Model! Create living worlds and stream them in real time, with persistent memory, interactivity, and physics-grounded generation of unbounded length. Try it now at https://www.visko.ai/models#orbis API available via @reactorworld Dynamic version: http://reactor.inc/sandbox?model=visko-orbis-dynamic Stable version: http://reactor.inc/sandbox?model=visko-orbis-stable

At Reactor we ❤️ open-source. We teamed up with @haoailab to ship an infinite live stream powered by FastVideo’s FastH3: https://twitch.tv/dereactor And we’re open-sourcing everything!

Last week, my friend @BernieSu (3x Emmy winner) invited me to his private screening, my first time experiencing immersive film. It’s an unprecedented format & the frontier of what’s possible when AI + creativity come together. I kept saying the commercial and creative space this could unlock is enormous. But the bottleneck was still latency. Their solution then was game-engine rendering. Just one week later, @fal launched MiniMax H3-Max, pushing generation speed to a completely whole new level. And today @levelsio put that capability straight into a 24/7 AI livestream product. It takes great taste and judgment to see what’s possible, and the conviction &execution to actually make it happen. We’re thrilled to be part of this, collaborating with good friends and partners to build entirely new product paradigms. What a time to live! amaze amaze amaze!!🪄🧗🏻‍♀️

45% preferred FastVideo FastH3 or are neutral compared with @MiniMax_AI H3. Our open-weight FastH3 achieves 15s generation in 13s and 14x speedup. 🚀 Big shoutout to the folks at @fal and @isidentical for helping us run an eval against H3. As an open source project we always appreciate all the help we can get. The entire team is quite excited by this result for a preview checkpoint trained on a fraction of our planned total compute and partial data. Excited for what our next versions can do!! Weights: https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree Blog: https://haoailab.com/blogs/fasth3-preview/ Thank you for your contribution to the open source H3 ecosystem @fal! https://x.com/isidentical/status/2093482587268522188

Speed is easy when you ignore quality. I can generate random pixels under 1 nanosecond and claim to be ♾x faster than H3 and call it H3-ultra-lightning-fast. But this is not how people should innovate on speed in open. Image and video models are notoriously hard to optimize and we @ fal spend 2-3x more time on evals and making sure optimizations work than actual kernel engineering work. But when you see people claiming they are X times faster than original while messing the quality to a degree that the outputs has nothing to do with original model, it is annoying. Numbers below are for this case, but this is not the first/only one doing it. I'd recommend the authors below, and everyone on the field to run their own evals. Without preference and quality evals in the loop, ai-slop-performance agents can just lead you into a way you generate random pixels and it is just dishonest to call it anything but a random-pixel-generator.

(1/6) Open Weight @MiniMax_AI FastH3 v1: Generate 15s 768p video in 13s 🚀 - FastVideo collab w/ @nuvalab + FastGen - Up to 14x speedup on @NVIDIAAI Blackwell GPU - Fully open so community can run and improve the acceleration recipe. The era of open weight video models just started, that calls for post training. With great community effort such as Minimax H3 Max based on @MiniMax_AI , we have more to share about how post training can improve speed, quality and most importantly, how it’s done, with open weights and recipes.

Introducing H3 Max, new post-trained video model by fal Research. H3 Max ranks #1 for overall quality, prompt understanding, and aesthetics against leading video models, on both first-party and third-party independent evaluations while generating a 5-second 720p video under 3 seconds. H3 Max is 50% off for the next week, making it the highest quality, fastest and cheapest model for overall video generation tasks.

Introducing H3 Max, new post-trained video model by fal Research. H3 Max ranks #1 for overall quality, prompt understanding, and aesthetics against leading video models, on both first-party and third-party independent evaluations while generating a 5-second 720p video under 3 seconds. H3 Max is 50% off for the next week, making it the highest quality, fastest and cheapest model for overall video generation tasks.