MakeIt3D

MiniMax H3 is a general-purpose omni-modal generation model that jointly understands multimodal contexts spanning text, images, video, and audio. It generates videos with native stereo sound at up to 2K resolution and 15 seconds in length, delivering content for advertising, branding, ecommerce, product design, UI/UX, gaming, and creative workflows. Users can combine reference types in one instruction, for example, transferring camera movement from a video, placing a character from an image into the scene, and matching vocals from an audio clip, while describing the relationships in natural language. H3 supports text-to-image, text-to-video with jointly generated audio, multi-shot modeling, text-to-audio, and generalized reference and editing across images, videos, and audio. Voice, sound effects, and music are modeled together. The model excels at instruction following, accurate text and brand presentation, and video-to-video motion transfer.

Grand prize winner of the Google I/O experiments challenge, Camarada is a true 3D camera that lets you capture 3D pictures and 3D videos, and enjoy amazing 3D effects/3D illusion right on your screen or share with friends. It supports cardboard VR viewers (stereoscope), red-cyan glasses (anaglyph), parallax view/cross view, and 3D TV. In the solo mode, you capture stereoscopic 3D images quickly by panning your smartphone from left to right. The 3D images are then converted to 3D GIF (smooth wigglegram) or hologram ("tilt card"), parallax view or cross view, or with cardboard VR viewers/red-cyan 3D glasses (anaglyph)/3D TV. This mode works for either portrait or landscape, and either front or back-facing cameras. So yes,3D selfies, too! In the dual-phone mode, Camarada syncs and links two smartphones to capture stereoscopic 3D videos. You then enjoy them in your cardboard VR viewer/stereoscope.