Henry Ruhs

As the year comes to a end, here’s an early look at what’s coming in 2026. This videos demonstrates what our team has been building over the past few weeks - and it’s just the beginning. Happy New Year!

@victormustar I would not post and brag about something like that, your whole business model is based on utilizing open weights and most of the time you sell inference on non-commercial models, which in my opinion is just another form of piracy.

the shift is real: in 2026 invest on AI builders 🤗

@kurono73 Single seat vs. Studio/Site license.

FaceFusion facefusion.io との協力により、HyperSwapモデルを搭載していますってあるけどこっちのプラグインとは別物ってこと？ HyperSwap Studio Pack $800 buymeacoffee.com/facefusion/e/5…

フェイスリプレイスメントプラグイン AE、Nuke、Davinci、Premiere 対応 認証済みのVFXスタジオのみにライセンスを提供だって。 aescripts.com/face-swapper/

@cocktailpeanut open weights !== open source

It was a good run, thank you Sora sensei for paving the way. Open source will take over from here.

A breakthrough in real-time video generation. As a research preview developed with @NVIDIA and shared at @NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

@MayorKingAI What it needs is a concept of open movies where creators can fork and push their changes to an existing movie. Similar to open source. Just a thought, nobody knows what the future holds.

@MayorKingAI Once you release a trending movie with "ai actors" the competition will copy them instantly and you'll cannibalize each other.

Filmmaking just changed With Higgsfield Soul Cast, creators can design their own AI actors Define their look, role, era and genre then reuse the same character across scenes and films Consistent characters Full cinematic control Everything about Soul Cast 👇

@xenovacom How to become a member of the onnx-community on huggingface? We like to contribute some models we converted over the years.

Announcing a new Claude Code feature: Remote Control. It's rolling out now to Max users in research preview. Try it with /remote-control Start local sessions from the terminal, then continue them from your phone. Take a walk, see the sun, walk your dog without losing your flow.

Between Gemini 3.1 and Claude 4.6 it's honestly wild what you can build. This feels like Google Earth and Palantir had a baby. Made this with all the geospatial bells and whistles -- real time plane & satellite tracking, real traffic cams in Austin, and even got a traffic system working. Panoptic detection on everything. Skinned the whole thing to look like a classified intelligence system. EO, FLIR, CRT. Got a bunch more stuff on the roadmap. This is fun.

Another 4 x 32GB RDIMM 5600 to complete our AI workstation. Guess how much I paid for this?

RIP Elevenlabs. Alibaba Qwen dropped this new AI text to speech Free & open source, <2GB vram, super fast. It has instant voice cloning, emotion control, and even voice design. Full tutorial: youtu.be/eC8mZceIy5k

Crystal Upscaler now works with videos 🤩 It took me 2 months, but it finally works We can now upscale any video to 4K - making everything super sharp - while keeping every detail

🚀 Code Released! EgoX: Egocentric Video Generation from a Single Exocentric Video ✨ 💻 The code is now available! You can generate egocentric videos just like in the demo, or use EgoX to transform your own exocentric videos into egocentric ones.

Apple dropped 2D-to-3D conversion just in time for the entire Epstein catalog to be converted into 3D Gaussian splats 💀

@synclabs_so only $5 per minute 😁

traditional AI models just move the mouth to match the audio. react-1 changes this entirely. it uses the audio to rebuild the whole performance: timing, emotion, and micro-expressions. instead of just looking dubbed, the actor looks like they meant every word in that language.

Try it out today 👇 segmind.com/models/faceswa…

oh my.. hows this even possible Meta just dropped SAM 3D, you can auto select any object in still image and.. turn them into high quality 3D model the model is free to download and test in playground link in comments

no more ad agencies.. in AI world you can now create 100k worth ads for a few bucks, use any actor &product and keep them consistent.. I spent a week to create this workflow, now you can copy and make it your own like & repost -> dm for free here's how it works:

I’m making a ComfyUI-integrated video editor to better storytelling with AI generated content. I’m about a week from finishing my project, so if you’d like to hear when I launch, I just made a waitlist: waitlister.me/p/gausian-ai I’d love to hear the community’s take on this idea!