Wan2.5
Wan2.5-Preview introduces a next-generation multimodal architecture designed to redefine visual generation across text, images, audio, and video. Its unified framework enables seamless multimodal inputs and outputs, powering deeper alignment through joint training across all media types. With advanced RLHF tuning, the model delivers superior video realism, expressive motion dynamics, and improved adherence to human preferences. Wan2.5 also excels in synchronized audio-video generation, supporting multi-voice output, sound effects, and cinematic-grade visuals. On the image side, it offers exceptional instruction following, creative design capabilities, and pixel-accurate editing for complex transformations. Together, these features make Wan2.5-Preview a breakthrough platform for high-fidelity content creation and multimodal storytelling.
Learn more
Ray2
Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion. It has a strong understanding of text instructions and can take images and video as input. Ray2 exhibits advanced capabilities as a result of being trained on Luma’s new multi-modal architecture scaled to 10x compute of Ray1. Ray2 marks the beginning of a new generation of video models capable of producing fast coherent motion, ultra-realistic details, and logical event sequences. This increases the success rate of usable generations and makes videos generated by Ray2 substantially more production-ready. Text-to-video generation is available in Ray2 now, with image-to-video, video-to-video, and editing capabilities coming soon. Ray2 brings a whole new level of motion fidelity. Smooth, cinematic, and jaw-dropping, transform your vision into reality. Tell your story with stunning, cinematic visuals. Ray2 lets you craft breathtaking scenes with precise camera movements.
Learn more
Gen-3
Gen-3 Alpha is the first of an upcoming series of models trained by Runway on a new infrastructure built for large-scale multimodal training. It is a major improvement in fidelity, consistency, and motion over Gen-2, and a step towards building General World Models.
Trained jointly on videos and images, Gen-3 Alpha will power Runway's Text to Video, Image to Video and Text to Image tools, existing control modes such as Motion Brush, Advanced Camera Controls, Director Mode as well as upcoming tools for more fine-grained control over structure, style, and motion.
Learn more
Marey
Marey is Moonvalley’s foundational AI video model engineered for world-class cinematography, offering filmmakers precision, consistency, and fidelity across every frame. It is the first commercially safe video model, trained exclusively on licensed, high-resolution footage to eliminate legal gray areas and safeguard intellectual property. Designed in collaboration with AI researchers and professional directors, Marey mirrors real production workflows to deliver production-grade output free of visual noise and ready for final delivery. Its creative control suite includes Camera Control, transforming 2D scenes into manipulable 3D environments for cinematic moves; Motion Transfer, applying timing and energy from reference clips to new subjects; Trajectory Control, drawing exact paths for object movement without prompts or rerolls; Keyframing, generating smooth transitions between reference images on a timeline; Reference, defining appearance and interaction of individual elements.
Learn more
