LitVideo

« An open-source video generator that combines text, images, video, and audio to produce 2K clips up to 15 seconds long, with native stereo sound generated in a single pass. API available »

« Generate 1080p 30fps videos up to 15 seconds long from text or images with consistent characters, cinematic camera movements, and realistic 3D physics. Features : multi-Shots, audio lip-sync,native audio, native-level text rendering, etc. »

« Generate 30-second native videos in a single pass, using up to 50 multimodal references (images, audio, videos) to ensure consistency in characters and scenes. Local edits are also more precise and don’t require regenerating the entire scene »

« Generate, edit, and extend videos from simple text or multimodal prompts using Google’s most advanced video model, integrated into the Gemini suite »

« Generate cinematic videos with synchronized native audio and more precise narrative control. Create realistic 6-second clips that can be extended up to 1 minute. Insert/delete elements and achieve smooth transitions via Flow »

« Create realistic 5s videos from text or images. Smooth movements, precise physics and stunning cinematic camera work! »

« An open-source video model that creates coherent multi-shot scenes with synchronized audio, edits real footage, and supports 4K HDR or RAW output. This video generator runs locally and is customizable»

« An AI video generator capable of producing native 4K clips up to 30 seconds long, featuring multiple linked shots, synchronized audio, and the same character appearing in each video. This AI model was created by Alibaba »