Genmo Launches Mochi 1: Open-Source Text-to-Video AI Model Challenges Industry Giants

4 Sources

Genmo releases Mochi 1, an open-source text-to-video AI model, offering high-quality video generation capabilities comparable to proprietary models. The launch is accompanied by a $28.4 million Series A funding round.

News article

Genmo Unveils Mochi 1: A Game-Changer in AI Video Generation

Genmo, an AI-based video generation platform, has launched Mochi 1, a state-of-the-art open-source text-to-video generation model. Released on October 22, Mochi 1 represents a significant advancement in AI-powered video creation, challenging proprietary models with its high-quality output and open-source nature 1.

Key Features and Capabilities

Mochi 1 boasts impressive capabilities, including:

  1. High-quality video generation from text prompts
  2. Realistic motion dynamics and physics simulation
  3. Strong adherence to text instructions
  4. 30 frames per second video output
  5. 480p resolution (with 720p HD version planned)

The model excels in understanding physics, including fluid movement, fur and hair simulation, and human motion 2.

Technical Specifications

Mochi 1 is built on a 10 billion parameter diffusion model, making it the largest open-source video generation model to date. It utilizes Genmo's proprietary Asymmetric Diffusion Transformer (AsymmDiT) architecture, which efficiently processes user prompts and compressed video tokens 2.

Open-Source Advantage and Accessibility

Unlike its proprietary competitors, Mochi 1 is released under the Apache 2.0 license, making it freely accessible to developers and researchers. This open-source approach aims to democratize AI video generation technology and foster innovation in the field 3.

Funding and Company Vision

Coinciding with the Mochi 1 launch, Genmo announced a $28.4 million Series A funding round led by NEA, with participation from several other investors. The company aims to "unlock the right brain of artificial general intelligence" and views Mochi 1 as a step towards building advanced world simulators 4.

Potential Applications and Impact

Mochi 1's release opens up possibilities across various fields:

  1. Research and development in video generation techniques
  2. Entertainment and advertising applications
  3. Educational content creation
  4. Synthetic data generation for robotics and autonomous vehicles
  5. Creative expression for artists and content creators 1

Challenges and Future Developments

While Mochi 1 represents a significant advancement, it still faces some limitations:

  1. Current 480p resolution (HD version planned)
  2. Potential for minor visual distortions in complex motion scenarios
  3. Struggles with animated content

Genmo plans to address these issues with the upcoming release of Mochi 1 HD, which will support 720p resolution and offer enhanced motion fidelity 4.

Explore today's top stories

Apple's AI Strategy: Subtle Integration Over Flashy Features

Apple's approach to AI focuses on seamless integration into existing apps and services, prioritizing user experience and trust over flashy features. This strategy aligns with consumer preferences and addresses concerns about AI reliability and privacy.

ZDNet logoPC Magazine logoBloomberg Business logo

19 Sources

Technology

21 hrs ago

Apple's AI Strategy: Subtle Integration Over Flashy Features

Apple Research Challenges AI Reasoning Models' Capabilities

Apple researchers have published a study questioning the true reasoning capabilities of advanced AI models, revealing fundamental limitations in their problem-solving abilities as complexity increases.

Tom's Hardware logoThe Register logoLive Science logo

13 Sources

Science and Research

13 hrs ago

Apple Research Challenges AI Reasoning Models' Capabilities

Getty Images vs. Stability AI: Landmark Copyright Trial Begins in London

A high-stakes legal battle between Getty Images and Stability AI commences in London's High Court, marking the first major copyright trial in the generative AI industry. The case centers on the alleged unauthorized use of Getty's images to train Stability AI's Stable Diffusion model.

Reuters logoAP NEWS logoThe Guardian logo

8 Sources

Policy and Regulation

13 hrs ago

Getty Images vs. Stability AI: Landmark Copyright Trial

Microsoft and Asus Unveil ROG Xbox Ally Handhelds: A New Era of Portable Gaming

Microsoft partners with Asus to launch two new handheld gaming devices, the ROG Xbox Ally and ROG Xbox Ally X, running Windows 11 and offering access to multiple game stores and Xbox services.

CNET logoPC Magazine logoTom's Hardware logo

16 Sources

Technology

21 hrs ago

Microsoft and Asus Unveil ROG Xbox Ally Handhelds: A New

Apple Unveils Foundation Models Framework, Empowering Developers with On-Device AI Capabilities

Apple introduces the Foundation Models framework at WWDC 2025, allowing developers to access on-device AI models for enhanced app functionality while prioritizing privacy and offline capabilities.

TechCrunch logoengadget logoAppleInsider logo

5 Sources

Technology

5 hrs ago

Apple Unveils Foundation Models Framework, Empowering
TheOutpost.ai

Your Daily Dose of Curated AI News

Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.

Β© 2025 Triveous Technologies Private Limited
Twitter logo
Instagram logo
LinkedIn logo