Genmo has launched Mochi 1, an open-source AI model for generating high-quality videos from text prompts. You can try it for free on this page.
According to VentureBeat, Genmo is claiming performance that rivals leading proprietary models like Runway’s Gen-3 Alpha and Luma AI’s Dream Machine. Available under the Apache 2.0 license, Mochi 1 allows users to access advanced video generation capabilities for free, in contrast to the expensive pricing of competing models. The current version supports 480p resolution, with plans for a higher-definition version, Mochi 1 HD, later this year. Genmo emphasizes the model’s strong adherence to user prompts and high-fidelity motion, aiming to democratize AI technology for broader accessibility.
Mochi 1 is built on a novel architecture designed for efficiency and visual reasoning, and it is the largest open-source video generation model released to date. While Genmo is committed to open-source innovation, details about the training data used for Mochi 1 remain undisclosed. The model has some limitations, including minor visual distortions and challenges with animated content.