Congrats to the team! Amazing to run a model of Muse Spark Open's caliber and scale this efficiently, right from your desk. Mac Studio keeps pushing the boundaries of on-device AI!

Official: Apple announces the $299 HomeView, a smart display for its revamped smart home strategy with facial recognition for personal content, Apple apps and FaceTime. bloomberg.com/news/features/…

something is coming. who wants early access? 👇

1/8) FastVideo FastH3 now runs on a single consumer machine: @NVIDIA RTX GPUs 💚, DGX Spark and @Apple Silicon 🍎 FastH3 V2 beats base @MiniMax_AI H3 in 8 steps. A 5 s 480p clip with audio takes 15 s on one RTX 5090. We also release FastH3 Trim: 4.2× smaller than base H3, and it runs in as little as 8 GB of GPU memory. Every clip here was generated locally. @NVIDIAAI @NVIDIARTXSpark

Introducing FLUX 3 Image. Control every pixel. Make precise multi-turn edits without changing any other pixel. Lay out the image exactly how you want using bounding boxes. Generate in up to 4K to preserve details. Use up to 10 references to compose an image. Commercial Weights available for companies running image generation at scale. Open Weights version of FLUX 3 Image is launching in the coming weeks.

Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon! It shows frontier performance in complex workflows, cyber defense and software engineering. Teams are using it extensively at Google, from coding to quantum computing, great feedback. Here’s a look at the benchmarks:

Here's a side-by-side comparison of the same edits on Ideogram 4.5 vs. GPT Image 2.5 Sunburst, Nano Banana Pro, and Nano Banana 2. GPT Image and Nano Banana outputs become unusable within a few edits, while Ideogram 4.5 stays clean edit after edit.

Introducing Ideogram 4.5, the most precise edit model. With each edit, leading models add artifacts, pixel shifts, and color changes. Ideogram 4.5 eliminates artifact buildup, making multi-turn editing possible. Live in Ideogram, the API, and launch partners. Open weights soon.

Introducing Native Resolution, the first VFX Week drop, plus two new IC-LoRAs: Refine and Restore. Native Resolution runs AI edits on 4K and 8K footage and long shots. Overlapping tiles keep the fine detail, all on a single GPU. 🧵

Today I retrained Live Wallpaper, a model I’ve worked on for a long time and that many people use. This time, I brought it to MiniMax H3 Ref2VA, my main base model lately. It may be niche, but you can find more details here: huggingface.co/Alissonerdx/M… civitai.red/models/1264662/l…

Don't know if you would see this @DHH, Please consider supporting more open source contributors: @ostrisai github.com/ostris @cocktailpeanut github.com/pinokiocomputer @Kijaidesign github.com/kijai/

The Omacom Foundation is becoming a premier sponsor of @0xSero’s work on local AI for the next three years, through his company Sybil Solutions! We’re going to collaborate on making local models work beautifully out of the box on Omarchy. omarchy.org/news/2026/09/oma…

We’re open-sourcing the Ming-Image-0.1-Design family: • Ming-Image-0.1-Design, 6B • Ming-Image-0.1-Design-Layer, 6B • Two open-source Agent Skills: the Ling UI Design Skill and the Image-to-Editable-PPT Skill Ming-Image-0.1-Design ranks #1 among open-weight models on Artificial Analysis’s UI/UX Design leaderboard. 🧵

I’ve released an experimental MiniMax H3 VFX Edit LoRA for ComfyUI. It uses your source video as a frame-aligned guide, aiming to apply only the requested change while preserving motion, timing, framing and the rest of the shot. Download: huggingface.co/Alissonerdx/M… civitai.red/models/2954203/v… #ComfyUI #MiniMaxH3 #AIvideo #VFX

we built muse from scratch, but it is definitely heavily inspired as a product by openclaw. After I used openclaw in january I bought hundreds of mac minis for the MSL team and lots of us fell in love with using openclaw (and other personal agents). @steipete is a genius and his harness was pioneering from the jump. I think a lot of people were inspired by it. our goal with muse was to build something like openclaw that we could make safe and secure and easy to use and scale to billions of people.

一年ぶりに自主制作を進めています！ 今回のテーマは仮想の鏡です。単純なミラー反転ではなく、立体的に世界が反転したらどうなるか。 Vista4D+Meridian+Minimax H3+ComfyUIの力を借りて表現しています。単一の動画からポイントクラウド化、それをBlenderで再度レイアウトして最後に推論をかけています。完成するまで定期的にメイキング投稿していく予定です！

Sorry to hear that! As you mentioned, we've been pretty clear on the commitment from NVIDIA to keep us open, neutral and silicon agnostic (cf that screenshot from the 8k filling). But we'll work hard with our actions in the coming years (like we did in the past 10) to show you that and hopefully regain your trust (in case this is not just a ragebait)!

ZCode is now open source, and the reported security issues have been addressed. github.com/zai-org/ZCode We take the community’s feedback very seriously and apologize for the concern and frustration these issues have caused. We have been working closely with the ZCode team to investigate and remediate the issues raised. Independent security reviews by third-party firms are now underway. We will share the findings and provide further updates as they become available. We sincerely appreciate the developer community’s feedback and continued scrutiny. We will continue to monitor the review process closely and provide updates.