
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

Adobe Firefly is a versatile AI-powered creative platform designed to help users generate and edit multimedia content with ease. It allows users to create images, videos, and audio using simple text prompts within an interactive and flexible workspace. The platform features tools like generative fill, image editing, and video editing, enabling users to refine and enhance their creations. Firefly also includes quick actions such as background removal, cropping, resizing, and format conversion to streamline workflows. Users can explore an infinite canvas for creative production and experiment with various styles and outputs. The platform encourages creativity by allowing users to remix content from a shared community gallery. With its intuitive design, it reduces the need for advanced technical skills. Firefly integrates AI capabilities to speed up content creation and editing processes. It supports both beginners and professionals in producing high-quality results. Overall, Adobe Firefly provides a powerful and accessible environment for modern digital creativity.
Learn more
Gemini Omni
Gemini Omni is an AI-powered multimodal video creation and editing platform developed by Google to help users transform ideas into cinematic-quality visual content using natural language interactions. The platform combines text, image, and video inputs to generate high-quality videos while simplifying traditionally complex video editing workflows through conversational AI capabilities. Gemini Omni allows users to perform advanced editing tasks such as cinematic zooming, background replacement, scene enhancement, and template-based production without needing specialized technical expertise or professional editing equipment. Users can upload footage from their camera roll, apply AI-driven modifications, and create polished videos using simple prompts and intuitive workflows. The platform also includes AI avatar generation capabilities that allow users to create personalized digital avatars that look and sound like them for more immersive and customized content creation. Gemini Omni is designed to make professional-grade video production more accessible for creators, marketers, businesses, and everyday users seeking faster and more flexible content generation tools. By combining multimodal AI generation with conversational editing controls, the platform reduces the complexity of traditional post-production and creative workflows. Gemini Omni is rolling out to Google AI Plus, Pro, and Ultra subscribers globally as part of Google’s expanding AI-powered creative ecosystem. Through AI-driven automation, multimodal generation, and intuitive editing experiences, Gemini Omni helps users create cinematic video content with greater speed, creativity, and ease.
Learn more
EaseGen
EaseGen is an innovative online platform that allows users to create images and short videos through text prompts and visual inputs. The platform provides a selection of models for both images and videos, enabling users to generate new visuals based on text, modify existing images with reference materials, and produce videos from either text or images. Depending on the model chosen, the video creation process can incorporate several reference materials, including images, audio, or specific frames, along with customizable settings for duration, resolution, aspect ratio, and sound. Users can review their generated outputs, refine their prompts and configurations, access previous creations, and download their final products. The platform's diverse examples and workflows cater to a wide range of applications, such as product visuals, e-commerce imagery, advertising content, social media posts, posters, thumbnails, narrative ideas, and creative experimentation. EaseGen also offers a free tier featuring basic models, alongside various paid subscription options and credit packages; the specifics of model access, generation limits, and credit pricing differ based on the selected plan and workflow. This flexibility allows users to find the best fit for their creative needs and budget.
Learn more