LTX builds open world models, AI systems that generate, simulate, and shape video, audio, and the physical world. Lightricks created LTX so that developers, studios, and enterprises can own the model they build on, not just rent access to someone else's.
The current release, LTX-2.3, is a 22B-parameter dual-stream diffusion transformer. It renders native 4K footage at up to 50fps and produces synchronized audio and video in one pass, no separate tools required. Independent benchmarks from Artificial Analysis place LTX in the top three AI video models worldwide.
There is no single way to work with LTX. Pull the open weights and run the model yourself on your own machines. Take a commercial license for on-premise deployment with full enterprise support. Or use LTX Studio, the packaged production suite for creative teams that want the model without managing the infrastructure. ElevenLabs, Asteria Film Co., Magnopus, and NVIDIA all build on it today.
If you need a quick clip for social media, look elsewhere. LTX exists for AI teams turning video, audio, and simulation into part of their own product, not a novelty.
Learn more
Google AI Studio is a comprehensive platform for discovering, building, and operating AI-powered applications at scale. It unifies Google’s leading AI models, including Gemini 3.5, Imagen, Veo, and Gemma, in a single workspace. Developers can test and refine prompts across text, image, audio, and video without switching tools. The platform is built around vibe coding, allowing users to create applications by simply describing their intent. Natural language inputs are transformed into functional AI apps with built-in features. Integrated deployment tools enable fast publishing with minimal configuration. Google AI Studio also provides centralized management for API keys, usage, and billing. Detailed analytics and logs offer visibility into performance and resource consumption. SDKs and APIs support seamless integration into existing systems. Extensive documentation accelerates learning and adoption. The platform is optimized for speed, scalability, and experimentation. Google AI Studio serves as a complete hub for vibe coding–driven AI development.
Learn more
Odyssey-2 Max
Odyssey-2 Max represents a cutting-edge real-time world simulation model that surpasses traditional generative AI by intricately understanding the physical world's dynamics and enabling continuous interactive experiences. As the third version in the Odyssey-2 lineup, it features a significant enhancement in scale, incorporating three times more parameters and ten times the computational power than the previous iteration, Odyssey-2 Pro, which leads to the emergence of new behaviors and improved stability and realism in simulations. Designed for precise replication of physics, human movement, interactions, and environmental transformations in real time, it provides uninterrupted visual output that responds immediately to user input rather than depending on static video sequences. Unlike conventional video models that generate brief, set sequences, Odyssey-2 Max allows for the creation of expansive simulations that evolve continuously, giving users the ability to interact with a vibrant and ever-changing environment. This groundbreaking methodology revolutionizes user engagement, as each session becomes distinctive and immersive, adapting uniquely to the new inputs provided by the user and ensuring a fresh experience every time. With its advanced capabilities, Odyssey-2 Max not only enhances the realism of simulations but also opens up new possibilities for creative expression and interaction within virtual worlds.
Learn more
Agora-1
Agora-1 introduces a groundbreaking multi-agent world model designed to enable real-time interactions between multiple participants, whether they are human beings or AI entities, in a shared simulated environment. This model marks the first in a series of multi-agent world models that seek to explore new collective experiences across diverse sectors, including gaming, robotics, defense, education, and core model development. Historically, world models have been proficient at producing high-quality simulations of various settings; however, they were constrained by the ability for only a single participant to interact with the simulated worlds at any given moment. Agora-1 transforms this limitation by allowing as many as four players to participate simultaneously within the same generated landscape. In this competitive deathmatch simulation, each player is fully engaged in the same world, as the model skillfully replicates player actions, maintains a cohesive world state, and broadcasts the rendered visuals to all participants, significantly enriching the immersive experience. This innovation not only enhances gameplay but also opens new avenues for cooperative and interactive engagements in numerous fields, paving the way for future developments in multi-agent collaboration. As a result, Agora-1 stands as a significant advancement in the realm of simulated environments and multi-agent interactions.
Learn more
