✦
Summary
Mochi 1 is an advanced open-source video generation model known for its high-fidelity motion and strong adherence to textual prompts. It marks a significant leap in the quality of motion and prompt alignment, pushing the boundaries of what's achievable in open-source video creation. Licensed under the permissive Apache 2.0 license, Mochi 1 is designed for both personal and commercial use, with a focus on photorealistic video generation rather than animated content. The model achieves smooth video output at 30 frames per second with durations up to 5.4 seconds, ensuring temporal coherence and realistic motion dynamics. This makes Mochi 1 an ideal tool for users seeking detailed control over characters, settings, and actions through text prompts.
Key Features
Open-source video generation model with Apache 2.0 license
High fidelity motion and strong prompt adherence
Smooth 30 fps video output up to 5.4 seconds
10 billion parameter diffusion model on Asymmetric Diffusion Transformer architecture
Efficient video compression via novel video VAE
Single T5-XXL model for prompt encoding with multi-modal self-attention
480p base model with upcoming HD 720p version
Hosted playground available for free trial
Applications in research, product development, creative expression, and robotics
About Mochi 1
Built on a novel Asymmetric Diffusion Transformer architecture, Mochi 1 is the largest video generative model openly released, with 10 billion parameters trained from scratch. It employs an efficient video VAE that compresses video data significantly, allowing the model to run effectively in community environments. The model's architecture smartly balances text and visual processing with multi-modal self-attention mechanisms, ensuring that the generated videos are both visually compelling and contextually accurate. Additionally, Mochi 1 uses a single T5-XXL language model to encode prompts, supporting complex reasoning over long video token contexts with 3D attention to capture space and time dimensions in video generation.
Mochi 1 is freely accessible through a hosted playground where users can try video generation from their own prompts in 480p resolution. Genmo plans to release an HD version later, supporting 720p with enhanced fidelity and smoother motion. The project is positioned as a research and creative tool with applications in entertainment, advertising, education, robotics, and synthetic data generation. Ongoing development aims to improve image-to-video capabilities and fine control over output styling. Mochi 1 underscores Genmo's mission to advance AI-driven creativity by enabling open research and fostering a community around video generation technologies.