Most AI video tools hand you a black box: closed weights, a subscription, and no way to see what is happening under the hood. LTX takes the opposite approach. Built by Lightricks, LTX is an open foundation model that generates and simulates across video, audio, and the physical world, and it puts the weights, the code, and the control in your hands.
At the center of the model is LTX-2.5, a 22B-parameter dual-stream diffusion transformer that produces native 4K video at up to 50 frames per second, with audio and video generated together in a single pass rather than stitched together afterward. Artificial Analysis, an independent benchmarking group, currently ranks LTX among the top three AI video models in the world.
You choose how you want to use it. Download the open weights and run LTX-2.5 on your own hardware. License the model for on-premise deployment backed by enterprise support. Or build directly on LTX Studio, the production suite that turns the model into a full creative workflow. Companies like ElevenLabs, Asteria Film Co., Magnopus, and NVIDIA already rely on LTX for their own work.
LTX is not built for one-off social clips. It is infrastructure for teams that generate motion, audio, and physical environments as part of their own products and pipelines.
Learn more
You can watch videos from anywhere, anytime, even offline. It's easy to download: simply copy the link from your browser, and then click 'Paste Link" in the application. You can save full playlists and channels on YouTube in high-quality and other video or audio formats. Download your YouTube Mix, Watch Later and Liked videos as well as private YouTube playlists. Receive new videos from your favorite YouTube channels automatically. You can feel the action around you with virtual reality videos. To experience the amazing VR experience in 360deg, download 360deg videos. You can bypass any restrictions placed by your Internet service provider to bypass your school firewall or workplace firewall. To access YouTube and other sites, set up an in-app proxy connection.
Learn more
HappyHorse 1.1
HappyHorse-1.1-T2V is a QwenCloud video generation model that creates videos from text descriptions. The model is designed to improve text-to-video quality through stronger semantic understanding, cinematic shot control, and dynamic motion rendering. HappyHorse-1.1-T2V helps users produce videos that better reflect the intent of a prompt, including scene atmosphere, character movement, physical dynamics, and visual consistency. It supports video generation at 480P, 720P, and 1080P, with pricing based on generated video seconds. Developers can call the model through the DashScope API and configure parameters such as resolution, ratio, and duration. The model is not open source and is offered as a hosted API through QwenCloud. Rate limits include 300 requests per minute, 5 concurrent requests, and an async queue limit of 500 tasks. QwenCloud also provides free quota for testing and API key access for production usage. By combining text-to-video generation, semantic prompt understanding, cinematic control, motion rendering, API access, and scalable rate limits, HappyHorse-1.1-T2V helps teams build AI video creation workflows.
Learn more
Gemini Omni Flash
Google has introduced Gemini Omni, a groundbreaking family of models that merges reasoning skills with creative capabilities, starting with video production. The flagship model, Gemini Omni Flash, possesses the remarkable ability to generate content from diverse inputs such as images, audio, video, and text, resulting in high-quality videos enriched by Gemini's comprehensive knowledge of the real world. By allowing users to edit video through a conversational interface, it ensures that each instruction seamlessly builds upon the previous one, maintaining character consistency, adhering to the laws of physics, and retaining continuity in scenes. Users are empowered to modify intricate details or entire environments, reimagine actions, introduce new characters or objects, alter surroundings, adjust camera perspectives, enhance styles, and execute multi-step edits without losing sight of the original narrative. Designed to seamlessly connect photorealism with impactful storytelling, Gemini Omni skillfully reasons about subsequent actions, drawing on an innate understanding of natural forces like gravity, kinetic energy, and fluid dynamics, which enhances the overall storytelling experience. This innovative approach not only simplifies video editing but also opens new avenues for creative expression, making it accessible to a broader audience.
Learn more
