Lightricks Launches 13B Parameters LTX Video Model, Breakthrough Rendering Approach Generates High-quality, Efficient AI Video 30X Faster Than Comparable Models
JERUSALEM and NEW YORK, May 6, 2025 /PRNewswire/ — Lightricks , a leader in AI-driven content creation technology, today announced the release of its LTX Video 13-billion-parameter model (LTXV-13B) – which may be the most advanced and efficient AI video generation model to date. This substantial upgrade dramatically increases quality while maintaining LTXV's unparalleled speed generating AI videos. The 13B model is available within the company's flagship storytelling platform, LTX Studio, shared with the open community and is being integrated across the Lightricks portfolio.
LTXV-13B introduces 'multiscale rendering,' a major technical breakthrough that delivers both speed and quality through a layered process. The model drafts in lower detail first to capture coarse motion using fewer resources. This draft then guides the next stages, where the model progressively adds structure, lighting, and micro-motion (and spending time where it matters most). The result is high-fidelity video built through deliberate, multi-scale generation, with render times that can be more than 30X faster than comparable models – without compromising visual realism.
The new 13B model represents a significant leap forward in Lightricks' generative AI capabilities, offering creators the ability to produce videos with stunning detail, coherence, and control. It utilizes the latest advancements in academia and the open source community, including unsampling controls and spatiotemporal guidance for video editing, and kernel optimization for running speeds.
Unlike other models that demand enterprise-grade GPU (and long rendering times), LTXV-13B delivers studio level video at unmatched speed, even on devices that creators already own, which differentiates LTX Video in the marketplace.
'The introduction of our 13B parameter LTX Video model marks a pivotal moment in AI video generation with the ability to generate fast, high-quality videos on consumer GPUs,' said Zeev Farbman, co-founder and CEO of Lightricks. 'Our users can now create content with more consistency, better quality, and tighter control. This new version of LTX Video runs on consumer hardware, while staying true to what makes all our products different – speed, creativity, and usability.'
While developing and refining the 13B model, Lightricks entered into a strategic partnership with leading media asset provider Getty Images . In December 2024, Lightricks entered an agreement with Shutterstock to leverage their licensed content. These kinds of collaborations have given Lightricks access to an extensive library of high-quality video assets for model training, reinforcing its mission to build ethically trained, visually compelling, and commercially safe generative tools.
The LTXV-13B model now empowers creators with even more control and flexibility, seamlessly supporting all of the platform's advanced creative tools, including:
Keyframe editing
Camera motion control
Character and scene-level motion adjustment
Multi-shot sequencing and editing
In support of startups and small businesses, Lightricks is offering the 13B model free to license for enterprises with under $10 million in annual revenue. This initiative and the release of all LTXV models in open source reflect Lightricks' commitment to making cutting-edge generative AI accessible to the next generation of creative companies and innovators. Open source versions of LTXV are available on Hugging Face (LTX-Video) and GitHub (LTX-Video) .
'By consistently refining our models and working with the open community, we've built an AI system that generates physically natural movement while preserving artistic control,' added Yoav HaCohen, Director of LTX Video at Lightricks.
Since launching LTX Video in November 2024, Lightricks has collaborated with researchers and open-source contributors to improve motion consistency, scene coherence, and creative adaptability. Key open-source advancements in LTXV-13B include:
VACE Model Inference – advanced video generation and editing tools, including reference-to-video (R2V). Details on GitHub
– advanced video generation and editing tools, including reference-to-video (R2V). Details on Unsampling Controls for Video Editing – Tools that reverse noise and refine frame granularity. Details on GitHub .
– Tools that reverse noise and refine frame granularity. Details on . Kernel Optimization – Efficient Q8 kernel usage allows performance scaling on lower-resource devices. Details on GitHub and HuggingFace .
With a growing library of models designed for diverse creative needs and a commitment to open development, Lightricks is shaping the future of generative AI video, bridging research-driven breakthroughs with real-world application. For more information about Lightricks, its products, technology, and open-source initiatives, visit www.lightricks.com .
View original content to download multimedia:https://www.prnewswire.com/news-releases/lightricks-launches-13b-parameters-ltx-video-model-breakthrough-rendering-approach-generates-high-quality-efficient-ai-video-30x-faster-than-comparable-models-302447660.html
SOURCE Lightricks
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Malaysian Reserve
20 hours ago
- Malaysian Reserve
Trumid Reports May Performance
Electronic bond trading platform announces record buy-side platform engagement NEW YORK, June 6, 2025 /PRNewswire/ — Trumid, a financial technology company and leading fixed income electronic trading platform, today announced trade volume and user participation highlights for May 2025. May Highlights: May marked another strong month of growth and deepening platform engagement, with record traded volume in Trumid RFQ and accelerating buy-side adoption across Trumid's list trading protocols. Reported Average Daily Volume (ADV) of $6.8B, up 30% year-over-year. A record number of buy-side traders traded daily on Trumid in May, with asset manager ADV up around 60%year-over-year, outpacing growth in overall Trumid volume. Trumid RFQ set another monthly record for volume and trade count, extending its 2025 streak of consecutive month-over-month growth. High response rates from Trumid's fully integrated RFQ responder network of major dealers and leading algorithmic liquidity providers drove protocol ADV and daily average trade count up 122% and 134% year-over-year, respectively. Around 70% more buy-side traders executed trades daily in Trumid RFQ compared to a year ago, with asset managers initiating a record number of lists during the month. Trumid's automated workflow and trade automation tools continued to deliver value for clients. 81% of eligible RFQ line items executed "no touch" via Trumid AutoPilot™ for RFQ in May. Designed for efficient execution, Trumid AutoPilot leverages real-time, client-defined parameters to allow the platform to seamlessly execute trades on their behalf. High response rates from Trumid's fully integrated RFQ responder network of major dealers and leading algorithmic liquidity providers drove protocol ADV and daily average trade count up 122% and 134% year-over-year, respectively. Around 70% more buy-side traders executed trades daily in Trumid RFQ compared to a year ago, with asset managers initiating a record number of lists during the month. Trumid's automated workflow and trade automation tools continued to deliver value for clients. 81% of eligible RFQ line items executed "no touch" via Trumid AutoPilot™ for RFQ in May. Designed for efficient execution, Trumid AutoPilot leverages real-time, client-defined parameters to allow the platform to seamlessly execute trades on their behalf. Trumid press +1 (212) 618-0300 press@ About Trumid Trumid is a financial technology company and fixed income electronic trading platform focused on US dollar-denominated Investment Grade, High Yield, Distressed, and Emerging Market bonds. Trumid optimizes the credit trading experience by combining agile technology and market expertise, with a focus on product design. The result is a differentiated ecosystem of protocols and trading solutions delivered within one intuitive platform. Learn more at © 2025 Trumid Holdings, LLC, and its affiliates. All rights reserved. Trumid Financial, LLC is a broker dealer registered with the U.S. Securities and Exchange Commission ("SEC") and is a member of FINRA and SIPC. Information included in this message does not constitute a trade confirmation or an offer or solicitation of an offer to buy/sell securities or any other products. There is no intention to offer products and services in countries or jurisdictions where such an offer would be unlawful under the relevant domestic law.
Malaysian Reserve
a day ago
- Malaysian Reserve
Wildfire Prevention Today and Tomorrow: PG&E Shares 2025 Wildfire Season Readiness Update, Showcases Local XPRIZE Wildfire Competitors
PG&E's Layers of Protection Are Working, Prevented a Major Wildfire in 2023 and 2024 SAN RAMON, Calif., June 6, 2025 /PRNewswire/ — Using artificial intelligence (AI) and machine learning to monitor wildfire conditions and deploying proven layers of wildfire protection to prevent wildfires, Pacific Gas and Electric Company (PG&E) shared its readiness ahead of peak wildfire season. These layers of protection helped prevent a major wildfire in 2023 and 2024. Today, at PG&E's Applied Technology Services lab, the company's research and development facility, PG&E shared details about how the layers of protection are applied throughout PG&E's service area to prevent wildfires. PG&E was joined by representatives of XPRIZE Wildfire and two local teams – Ember Guard and Rain – who bring AI power and autonomous firefighting to the competition. PG&E is a proud sponsor of XPRIZE Wildfire and its work to build a pipeline of new technologies that support advanced wildfire mitigation, detection and response. Today's Wildfire Resilience from Layers of Protection Undergrounding Powerlines in high fire-risk areas to permanently eliminate ignition risk. PG&E has undergrounded approximately 915 miles of powerlines since 2021 and plans to have nearly 1,600 total miles of powerlines underground by the end of 2026. Overhead System Upgrades include the installation of strengthened power poles and covered powerlines. This work reduces wildfire ignition risk by nearly 67% once completed. PG&E has completed more than 1,430 miles of overhead system upgrades since 2018 and plans to complete nearly 1,900 total miles of system upgrades by the end of 2026. Situational Awareness Improvements including the deployment of a state-wide network of nearly 1,600 weather stations, of which 1,400 are artificial intelligence (AI) and machine learning enabled, and more than 650 high-definition wildfire cameras. The AI enabled cameras process data and provide automated wildfire notifications. Enhanced Powerline Safety Settings (EPSS) automatically turn off power within one-tenth of a second, or faster, if a wildfire hazard is detected. These settings protect 1.8 million PG&E customers in areas with elevated or extreme wildfire risk. In 2024, these settings contributed to more than a 65% reduction in reportable ignitions, compared to the 2018-2020 average. More than half of customers protected by EPSS did not experience a power outage while EPSS was enabled in 2024, and the average duration of outages on an EPSS-enabled circuit decreased 17% from the prior two-year average. Vegetation Management programs continue to evolve using a data-driven, risk-informed approach to help reduce both outages and potential ignitions caused by vegetation contacting PG&E's equipment. Over the past five years, PG&E has inspected, trimmed or removed over 960,000 trees and other types of vegetation in our service area. Drone inspections that more efficiently provide a bird's eye view of assets from the ground and air. Public Safety Power Shutoffs are a last resort during extreme weather conditions to reduce the risk of catastrophic fire. PG&E's experienced meteorologists use cutting-edge weather models to forecast wildfire risk at a granular level to determine the transmission and distribution circuits that will get de-energized. 'Rather than being reactive to conditions, our wildfire work proactively protects and prevents wildfire. We're keeping our system safe while we build resilience for the future. This work is essential in light of extreme weather and extended wildfire seasons,' said PG&E Wildfire Mitigation Vice President Andy Abranches. Tomorrow's XPRIZE Goal: Detect Earlier, Extinguish Faster As wildfire conditions are dynamic from year to year, PG&E is committed to supporting a pipeline of new research, development and innovation to address climate-driven wildfire challenges. PG&E today joined XPRIZE Wildfire and two local teams participating in the four-year, $11 million competition to accelerate the speed of detection and suppression of destructive wildfires. XPRIZE Wildfire encourages teams from around the world to innovate around a wide range of firefighting technologies across two complementary tracks designed to transform how potentially catastrophic fires are detected, managed and suppressed. PG&E is the co-title sponsor of XPRIZE Wildfire along with the Gordon and Betty Moore Foundation. 'For 30 years, XPRIZE has spurred innovation to address the world's most pressing challenges. In 2023, we launched XPRIZE Wildfire with a goal to end destructive wildfires,' said XPRIZE Wildfire Program Director Andrea Santy. 'Today, we have an incredible global cohort of dozens of teams making monumental strides towards developing solutions to reach this audacious goal.' One of the Bay Area teams showcased at the event was Palo Alto-based Ember Guard, a cross-disciplinary team led by Ahvish Roy, founder of ARX, and supported by Sangram Ganguly, Chief Technology Officer of Rhombus Power. It uses deep learning along with AI to produce a scalable cloud-based high-resolution wildfire model that forecasts the likely propagation and intensity of a wildfire so that firefighters can prioritize their limited resources Also participating was Alameda-based Rain, which recently showcased autonomous wildfire suppression technology in California. A Black Hawk helicopter equipped with wildfire mission autonomy from Rain and MATRIX™ autonomy technology from Sikorsky, a Lockheed Martin company, conducted a demonstration of a wide range of wildfire response missions and tasks, including finding and suppressing early-state wildfires, all commanded via tablet. Rain is a participant in the Electric Program Investment Charge program, a research and development project. Learn more about PG&E's wildfire safety efforts at About PG&EPacific Gas and Electric Company, a subsidiary of PG&E Corporation (NYSE:PCG), is a combined natural gas and electric utility serving more than 16 million people across 70,000 square miles in Northern and Central California. For more information, visit and
Malaysian Reserve
a day ago
- Malaysian Reserve
Uneven tech jobs report clouded by a confluence of factors, CompTIA finds
Economic, geopolitical and technological uncertainties weigh on tech hiring DOWNERS GROVE, Ill., June 6, 2025 /PRNewswire/ — Uneasiness continues to weigh on tech hiring activity, according to CompTIA, the leading global provider of vendor-neutral information technology (IT) training and certification products. Tech sector companies added a modest 1,571 net new employees in May, analysis of U.S. Bureau of Labor Statistics (BLS) #JobsReport data reveals.1 Job growth in cloud infrastructure and tech services was offset by reductions in the telecommunications sector. Tech occupation employment across the economy declined by an estimated 131,000 positions.2 With prior month employment gains, tech occupation employment remains in the positive for the year. The unemployment rate for tech occupations for May was 3.4%, roughly in line with April's 3.5% rate. The tech unemployment rate continues to sit below the national rate. 'It is undoubtedly a challenging time for employers and job seekers facing uncertainty on multiple fronts,' said Tim Herbert, chief research officer, CompTIA. 'At the same time, it requires taking a measured approach given the data continues to hold up reasonably well.' Active employer job postings for tech positions reached nearly 470,000 last month, including 208,791 new postings added in May.3 There was solid employer demand for software developers and engineers, tech support specialists, systems engineers and architects and cybersecurity engineers and architects. Hiring for artificial intelligence (AI) positions and those requiring AI skills continues to increase at a rapid pace, according to CompTIA analysis of Lightcast data. Employer job postings related to AI are up 117% year-to-date year-over-year. Skills-based hiring remains core to many employers' recruiting strategies. About one-half of all tech job postings did not specify a need for a four-year academic degree, but rather some combination of work experience, training and industry-recognized certification. The finance and insurance industry sector saw a 21% increase in new tech occupation job postings in May, while new tech job openings in the retail sector rose by 16%. The New York City, Washington and Dallas metropolitan areas had the highest volumes of tech job postings for the month. Four metro markets experienced double-digit percentage increases in tech job postings from April to May: Virginia Beach (+25%), Colorado Springs (+16%), San Diego (15%) and Seattle (+10%). The 'CompTIA Tech Jobs Report' is available here. About CompTIA CompTIA Inc. is the leading global provider of vendor-neutral information technology (IT) training and certification products. CompTIA unlocks potential in millions of aspiring technology professionals and careers changers. Working in partnership with thousands of academic institutions and training providers, CompTIA helps students build career-ready skills through best-in-class learning solutions, industry-recognized certifications and career resources. Learn more at Media Contact Steven Ostrowski CompTIA sostrowski@ +1.630.678.8468 1 Labor market data from the U.S. Bureau of Labor Statistics and employer job postings from Lightcast may be subject to backward revisions.2 Monthly occupation level data from the U.S. Bureau of Labor Statistics tends to experience higher levels of variance and volatility.3 Active job postings include new postings added by employers in the latest month and open postings carried over from previous months.
