LTX-2.5 Launches with Fast AI Video Generation and Open Weights Integration
- Published
- Source
- Venturebeat.com
LTX, a company spun out of Lightricks, has launched LTX-2.5, an advanced open-weights video model that can generate a 10-second video from an image in just 6.8 seconds using NVIDIA superchips. This model is now integrated into ComfyUI and available on Hugging Face, supporting organizations with under $10 million in annual revenue for free.
The significance of LTX-2.5 lies in its innovative features, including a new diffusion video decoder that enhances video quality and native multishot generation for consistent outputs. LTX claims its model has surpassed 33 million downloads, making it the most popular open world model line, and it aims to provide flexibility and efficiency in video generation compared to closed API competitors.
Looking ahead, LTX is focused on expanding its capabilities and refining its technology. The company emphasizes the importance of open weights for diverse use cases in video and world models, contrasting its approach with the trend towards closed models in the industry. No further timeline was disclosed at the time of publication.
Original report
LTX-2.5 can generate a 10-second AI video from an image in just 6.8 seconds on Nvidia superchips — and it's open weights
Venturebeat.com · [email protected] (Carl Franzen)This briefing is an independently written summary based on publicly available reporting and is provided for industry information and news discovery. The original report and source publication are credited and linked where applicable. RobotToday does not claim ownership of third-party source material.
Rights concerns? Contact [email protected] with the relevant URL and details. We will review the matter and take appropriate action where warranted.
More related news
- 1
- 2
- 3
- 4
- 5
-
6
RobotToday Weekly November 9–13, 2026 RobotToday · 3 days ago
- 7
- 8
- 9
- 10
- 11
- 12
Related Suppliers
Hugging Face
Open-source AI platform and robotics enabler; home of LeRobot, 2M+ models, and the Reachy Mini desktop robot.
Pollen Robotics
Bordeaux, France humanoid-robot maker founded 2016 by Matthieu Lapeyre and Pierre Rouanet, now part of Hugging Face since April 2025.
Arcee AI
U.S. AI model lab building efficient open-weight small language and foundation models that run on edge, on-prem or cloud.
Allen Institute for Artificial Intelligence
Seattle non-profit AI institute founded by Paul Allen; releases fully open robot models (MolmoAct, MolmoBot) and simulators (AI2-THOR, MolmoSpaces).
Runway AI, Inc.
US AI research company building general world models (GWM-1) for video generation and a robot-learning platform for policy inference, sim evaluation and data.
Claru
Reka AI's training-data unit, capturing egocentric video with 10,000+ wearable-camera collectors plus teleoperation and manipulation data for robot learning.
NVIDIA Robotics
NVIDIA robotics division delivering Isaac simulation and training tools, Jetson edge compute modules, and Omniverse digital twin frameworks for physical AI.
Deci AI (Acquired by NVIDIA)
Israeli deep learning optimization startup acquired by NVIDIA in May 2024 for ~$300M; known for AutoNAC neural architecture search technology.
commissure Inc.
University of Tokyo spin-off founded 2023 in Tokyo making tactile sensing, haptic devices and touch-data tools for robot imitation learning; NEDO NEP pick 2026.
TME US, LLC
Atlanta-based US arm of Poland's Transfer Multisort Elektronik; distributes over 1.5 million electronic and automation components worldwide.
DBR77 Robotics
Industrial digital-transformation platform pairing an automation-integrator marketplace with IIoT, Digital Twin and plant-operations software for manufacturers.
Elekta AB
Swedish medical technology company founded in 1972, producing radiation therapy and radiosurgery systems including the Leksell Gamma Knife for cancer treatment.
Robotics needs a service framework.
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Join the RobotToday community on LinkedIn
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.