AI News
MiniMax's H3 is the first open-source model to top an AI video ranking
The Decoder · Aug 3, 2026 · 2 min read
For the first time, an open-weight model sits at the top of a major AI video benchmark. China's MiniMax released H3, a...
Topic: video-generation
14 articles
Explore our coverage of video-generation — 14 curated articles, summaries, and related resources from the Inblix archive.
AI News
MiniMax H3 folds 6 video models into one and ships 2K for $1.95 a clip
MarkTechPost · Aug 1, 2026 · 2 min read
MiniMax just erased the boundary between video generation and video editing. Their new H3 model, live today, isn't a te...
AI News
DeepMind: Video generators are the world models CV has been waiting for
The Decoder · Jul 19, 2026 · 2 min read
Google DeepMind just dropped a paper arguing that the universal training task computer vision has been missing was hidi...
Product
Sora is OpenAI's gambit to build a 'world simulator'
OpenAI Blog · Jul 17, 2026 · 3 min read
OpenAI just pulled back the curtain on Sora, a new diffusion model that generates up to a full minute of high-fidelity...
Product
OpenAI Quietly Kills Sora Video Tool After Just 16 Months
OpenAI Blog · Jul 15, 2026 · 2 min read
OpenAI has officially shuttered its standalone Sora video generation product as of April 26, 2026, pulling the plug on...
Product
OpenAI launches Sora video model built on visual 'patches'
OpenAI Blog · Jul 15, 2026 · 2 min read
OpenAI has finally pulled back the curtain on Sora, its text-to-video model that turns prompts, still images, or existi...
Product
OpenAI launches Sora Turbo, but physics remain wonky
OpenAI Blog · Jul 15, 2026 · 3 min read
OpenAI just pulled Sora out of research preview and slapped it onto sora.com as a proper product. It's not the same mod...
Startups
PixVerse hits $2B valuation with $439M raise as video AI race narrows
TechCrunch AI · Jul 14, 2026 · 2 min read
Singapore's PixVerse just closed a Series C extension that brings its total raise to $439 million and pushes its valuat...
Product
Invideo AI's 50M users are slashing video production from a full day to 30 minutes
OpenAI Blog · Jul 13, 2026 · 2 min read
The old way of making a marketing video involved timelines, multiple software tools, and a lot of tedious grunt work. I...
Product
OpenAI Drops Sora 2, Then Kills the Entire Sora Product
OpenAI Blog · Jul 12, 2026 · 3 min read
OpenAI just pulled a head-spinning move: unveiling Sora 2, a genuinely impressive leap in video generation, while simul...
Research
Overworld's Waypoint-1 streams AI gameplay at 60 FPS on a single 5090
Hugging Face Blog · Jan 20, 2026 · 2 min read
The gulf between AI world models that produce slick demo reels and those you can actually interact with has been vast....
Research
Hugging Face offloads VAE decoding to the cloud, slashing GPU memory for Flux and video models
Hugging Face Blog · Feb 24, 2025 · 2 min read
Running a cutting-edge image or video model on a consumer GPU often hits a wall—not during the diffusion process itself...
Research
Filtering 1,493 videos down to just 47: The brutal reality of building clean AI video datasets
Hugging Face Blog · Feb 12, 2025 · 2 min read
If you've ever wondered why fine-tuned video models often produce glitchy, watermarked, or just plain ugly outputs, the...
Research
Open video models still can't touch image AI's 'Stable Diffusion moment'
Hugging Face Blog · Jan 27, 2025 · 2 min read
If you've been waiting for open-source video generation to have its Stable Diffusion moment, keep waiting. A new deep-d...