Muse
Microsoft has unveiled Muse, a groundbreaking generative AI model designed to revolutionize gameplay ideation. Developed in collaboration with Ninja Theory, Muse is a World and Human Action Model (WHAM) trained on data from the game Bleeding Edge. This AI model possesses a comprehensive understanding of 3D game environments, including physics and player interactions, enabling it to generate consistent and diverse gameplay sequences. Muse can produce game visuals and predict controller actions, facilitating rapid prototyping and creative exploration for game developers. By analyzing over 1 billion images and actions, Muse demonstrates the potential to assist in game preservation by recreating classic titles for modern platforms. While still in the early stages, with current outputs at a resolution of 300×180 pixels, Muse represents a significant advancement in integrating AI into the game development process, aiming to enhance, not replace, human creativity.
Learn more
C-Radiant
C-Radiant is an add-on module that provides physics-based spectral rendering and autogain, noise and sensor special effects for Aechelon Technology's pC-Nova image generator using advanced shader technology, without any need for hardware post-processing sensor solutions. Together with Aechelon Technology's C-Genesis geo-specific database architecture and tool set, C-Radiant spectral rendering allows the use of a single, common run-time and database for any existing or future sensor. Material descriptions in the database are defined not for just for one band but across the spectrum, enabling the generation of correlated multiple sensors such as Night Vision Goggles (NVG), Forward Looking InfraRed (FLIR) and Radar. This ensures perfect mutual correlation on a per-pixel level at 60Hz between the Out-The-Window and all sensors.
Learn more
Muse Video
Muse Video is Meta’s upcoming video generation model from Meta Superintelligence Labs, previewed alongside the launch of Muse Image. The model is built on the same pretraining foundation as Muse Image and is designed to generate high-fidelity videos with native audio support. Muse Video focuses on prompt adherence, visual realism, temporal consistency, and the ability to create short scenes with clear motion, continuity, and audio context. It can generate a wide range of video styles, including cinematic footage, UGC-style ads, animal scenes, product commercials, handheld point-of-view clips, and realistic moments with sound effects, voices, and music. Meta is continuing to improve areas such as audio-video synchronization and physically accurate fast motion before broader release. Coming soon to creators and Meta AI, Muse Video is positioned as a powerful tool for generating dynamic media across Meta’s creative ecosystem.
Learn more
Muse Spark 1.1
Muse Spark 1.1 is a multimodal reasoning model from Meta Superintelligence Labs built for agentic tasks, coding, computer use, tool use, and multimodal understanding. The model improves on the original Muse Spark with stronger performance in planning, orchestration, long-context work, coding workflows, and external app interactions. Muse Spark 1.1 can manage a 1 million token context window, remember earlier actions, retrieve important information, compact context, and delegate tasks across parallel subagents. It is designed to operate across tools, MCP servers, custom skills, browsers, native apps, scripts, images, video, PDFs, and audio-based workflows. Developers can access Muse Spark 1.1 through the new Meta Model API public preview, while users can try it in Thinking mode in the Meta AI app and on meta.ai.
Learn more
