Most AI video tools hand you a black box: closed weights, a subscription, and no way to see what is happening under the hood. LTX takes the opposite approach. Built by Lightricks, LTX is an open foundation model that generates and simulates across video, audio, and the physical world, and it puts the weights, the code, and the control in your hands.
At the center of the model is LTX-2.5, a 22B-parameter dual-stream diffusion transformer that produces native 4K video at up to 50 frames per second, with audio and video generated together in a single pass rather than stitched together afterward. Artificial Analysis, an independent benchmarking group, currently ranks LTX among the top three AI video models in the world.
You choose how you want to use it. Download the open weights and run LTX-2.5 on your own hardware. License the model for on-premise deployment backed by enterprise support. Or build directly on LTX Studio, the production suite that turns the model into a full creative workflow. Companies like ElevenLabs, Asteria Film Co., Magnopus, and NVIDIA already rely on LTX for their own work.
LTX is not built for one-off social clips. It is infrastructure for teams that generate motion, audio, and physical environments as part of their own products and pipelines.
Learn more
Switcher Studio allows you to capture video from multiple angles and edit it in real-time. This will allow you to connect with your community in a more engaging way. You can stream it live or save it for later. Your audience will be attracted to you with relevant content. Make it look great. There's no need to purchase, lug or learn largeequipment. Switcher is compatible with iPads and iPhones. Switcher is so intuitive that anyone can create amazing video with it. You don't need to hire outside videographers or producers. It takes an hour to edit every minute of edited video. Every minute of live-editing takes, well, one second. You can share every moment, live or recorded, external or internal, with video -- no matter what it holds.
Learn more
Stable 3D
Creating 3D content is often a challenging and labor-intensive endeavor for graphic designers, digital artists, and game developers, sometimes requiring extensive hours or even days to produce a moderately intricate 3D object. To address this, Stability AI is excited to announce a private preview of Stable 3D, an innovative solution that automates the generation of concept-quality textured 3D objects, significantly reducing the difficulty involved and enabling users without expertise to produce a draft-quality 3D model in just a few minutes by choosing an image, illustration, or by providing a text prompt. The 3D objects generated through Stable 3D are provided in the widely-used ".obj" file format, allowing for further refinement in 3D software like Blender and Maya, or seamless integration into game engines such as Unreal Engine 5 or Unity. This breakthrough technology not only streamlines the creative process but also opens up new possibilities for those looking to explore 3D modeling without extensive training.
Learn more
VRIN 3D
VRIN 3D is a mobile application designed for 3D scanning, allowing users to quickly generate a 3D model of an object by capturing images from various angles in under three minutes. The app stands out for its user-friendly interface, speed, and affordability compared to traditional methods of 3D modeling and scanning. Users can export their 3D models into six different file formats, receive a web viewer link, and obtain HTML code for easy sharing. Additionally, VRIN 3D includes a web-based viewer and editor that facilitates organization and modification of scanned 3D models. Notable features of VRIN 3D include advanced AI retouching to enhance materials and textures, AI-driven shape refinement for improved accuracy, and adjustable polygon settings to tailor file sizes to user needs. With its innovative capabilities, VRIN 3D is poised to revolutionize the way individuals and businesses approach 3D representation.
Learn more
