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!!🪄🧗🏻‍♀️

MiniMax H3-Max combines SOTA video quality with a step-change in generation speed, making high-quality video practical for many more real-world applications at scale. H3-Max also demonstrates the potential of Miniax H3 base model while pushing the frontier of open multimodal models forward. We’ve worked closely with @fal since day 1. @fal brings deep expertise in generative AI infrastructure and the ability to bring frontier models into production quickly and reliably. We’re excited to bring MiniMax H3-Max to developers, creators, and businesses worldwide together with @fal~ Keep rolling!

2 yrs ago when we first launched @Hailuo_AI, @runwayml has been setting an incredibly high bar for content, aesthetics, and technical quality, which we were genuinely inspired by it still every day. So happy and meaningful that we finally get to collab- the inspiration has come full circle now~

This was from last summer when our cofounder, sales lead, and I (all females) were on a roadshow, I crashed on different sofas for two weeks just like in college. Kinda miss it now lolll #onlyinsf#

As one of the few who’s constantly traveling back and forth between SF and China (Shanghai, HK, Shenzhen, Beijing), I’ve been seeing a fast-growing trend since last year that more and more of the leading forces in the industry are coming to China- and discovered tons of unexpected surprises👀 I have 100x photos sitting in my storage and way too lazy to post them 😆 Lmk if you’re planning to visit! We’ll make sure you get to experience the best (and most fun) parts of Shanghai!!

Half a year ago we open-sourced our Visual Tokenizer Pre-training (VTP) work, the first to validate a scaling law for visual tokenizers. Back then I said “I’m sure the industry will recognize the value of this work soon”😏 And here we go~ pretty cool to see more people exploring this direction ever since.

We put explanations in the license that there are no regional restrictions. However, in the EU we follow conventions similar to LTX and Hunyuan; while in the US, due to local laws and regulations and the ongoing legal situation with Disney, users are required to complete an additional form and sign a waiver.

My first SIGGRAPH! If you’re attending, let’s coffee and talk all things graphics, AI, and creativity btw this was my graduation headshot almost 10yrs ago and the gray dress is now my precious 5-year-old pajama😆 Always happy to be back in LA✌️ #ForeverTrojan#