Odyssey-2 Pro
Odyssey-2 Pro is a frontier general-purpose world model that generates continuous, interactive simulations you can integrate into products via the Odyssey API, marking a pivotal moment for world models similar to GPT-2 in language. It’s trained on large amounts of video and interaction data to learn how the world evolves frame-by-frame and outputs minutes-long simulations that can be interacted with in real time, not fixed short clips. Odyssey-2 Pro delivers improved physics, richer dynamics, more authentic behaviors, and sharper visuals by streaming 720p video at up to ~22 FPS that responds instantly to prompts and actions, and it supports embedding interactive streams, viewable streams, and parameterized simulations into applications with simple SDKs in JavaScript and Python. Developers can integrate the model with under ten lines of code to create open-ended, interactive video experiences where users’ inputs shape evolving scenes.
Learn more
Gemini Omni Flash
Gemini Omni is Google’s new model family where Gemini’s ability to reason meets the ability to create, starting with video. The first model in the family, Gemini Omni Flash, can create anything from any input by combining images, audio, video, and text as input, then generating high-quality videos grounded in Gemini’s real-world knowledge. It gives users an easier way to edit video through conversation, where every instruction builds on the last, characters stay consistent, physics hold up, and the scene remembers what came before. Users can transform specific details or entire worlds, reimagine action, add new characters or objects, change environments, adjust camera angles, refine styles, and build multi-turn edits without losing the thread of the original scene. Gemini Omni is designed to bridge photorealism and meaningful storytelling by reasoning about what should happen next, using an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics.
Learn more
Agora-1
Agora-1 is a multi-agent world model that enables multiple participants, human or AI, to share and interact within the same world simulation in real time. It is the first in a series of multi-agent world models exploring how world models can enable new shared experiences across gaming, robotics, defense, education, foundation models, and more. World models generate high-fidelity simulations of arbitrary environments, but until now, they have largely been limited to a single active participant inside those simulated worlds. Agora-1 introduces multi-agent world simulations by allowing up to four players to interact in the same generated world at once. Players are matched into a shared deathmatch simulation, where every participant interacts with the same world simultaneously while the model simulates player actions, maintains shared world state, and streams generated pixels to each player.
Learn more
FLUX 3
FLUX 3 is a multimodal foundation model that jointly learns from images, video, and audio within one unified architecture, building a representation of how objects hold together, how things move, and how events sound. Built on the Self-Flow approach, it aligns multimodal generation and understanding in the same backbone so each modality constrains the others, sound matches impact, motion follows physical properties, and future events follow from the past. FLUX 3 can mix modalities and jointly generate images, video, and native audio from text prompts or references such as images, video, and audio. Its video capabilities include text-to-video, image-to-video animation, video-to-video transformation, generative video-and-audio continuation, keyframe-controlled transitions, multilingual dialogue, animated typography, diverse styles and aspect ratios, and agentic chaining into longer multi-shot sequences.
Learn more
