Connect with us

Technology

Creatify Labs launches Boreal-H3, a MiniMax H3 video model post-trained for advertising

Published

on

Boreal-H3 scores a third higher than its MiniMax H3 base on Creatify’s Ads Quality Index and costs $0.04 per second, about one-twelfth the price of Seedance 2.5.

MOUNTAIN VIEW, Calif., Oct. 2, 2026 /PRNewswire-PRWeb/ — Creatify Labs today launched Boreal-H3, an AI video model for ads built by post-training MiniMax H3 in partnership with MiniMax. Creatify trained the model on the work an ad has to do: keep the product from the reference image intact, deliver natural creator performances, and carry out the brief as written. In the company’s evaluation, Boreal-H3 scored 133.3 on its Ads Quality Index, where MiniMax H3 is 100, the highest score among the frontier video models compared. At $0.04 per second at 768p, it costs about 12 times less than Seedance 2.5, which runs at roughly $0.47 per second.

Boreal-H3 is the second model in the Boreal family, following the original Boreal released earlier this month. Where the first Boreal was built for realtime generation at one cent per second, Boreal-H3 targets the details an advertiser checks first: whether the label is readable, whether the packaging keeps its shape, and whether the creator stays the same person from the first frame to the last.

Ad quality as the benchmark

The Ads Quality Index measures how often a model produces a clip that works as an ad. A clip passes only when prompt following, reference consistency and visual realism each score 6 out of 10 or higher, and each model’s pass rate is indexed against MiniMax H3’s. Boreal-H3 scored 133.3, ahead of Omni 1.1 Flash at 122.2, Seedance 2.5 at 118.1 and Wan 3.0 Prime at 111.1.

On reference fidelity, scored at a stricter 7 out of 10 threshold, Boreal-H3 reached 85.3%, ahead of MiniMax H3 at 82.4%, Wan 3.0 Prime at 79.4%, Seedance 2.5 at 71.9% and Omni 1.1 Flash at 70.6%. Creatify’s automated judges were validated against human preferences, and its human studies used anonymized, randomized outputs.

The product stays the product, and the creator stays the creator

Against its MiniMax H3 base, Boreal-H3 raised subject consistency from 83.3% to 94.4%, keeping the product and the creator recognizably the same across a clip. On a set of difficult production briefs, it raised brief completion from 27.8% to 50.0% and cut visible defects from 1.11 to 0.33 per clip, a 70% reduction.

The model is also built for the performance side of a UGC ad. Boreal-H3 handles complex dialogue and multi-avatar conversations, with a focus on clear speech, natural pacing and a creator who can handle the product while speaking. Product demonstrations get the same attention, with cause-and-effect actions such as a vacuum leaving a clean path or a pour that behaves like liquid.

More control over every shot

Boreal-H3 gives creative teams two ways to direct a shot. Keyframe control, in image-to-video, preserves the subject and visual style of an opening frame, with an optional ending frame to set exactly where the shot lands. Multi-reference control, in reference-to-video, combines up to 9 images, 3 videos and 3 audio clips into a single coherent shot. Text-to-video is also supported, and the model follows camera direction with natural transitions between scenes.

Faster and cheaper iteration

Boreal-H3 generates video at 1.1 seconds per video-second at 768p, so a 10-second clip takes about 11 seconds and costs $0.40. In the same comparison, Seedance 2.5 ran at 46.5 seconds per video-second and about $0.47 per second, which makes Boreal-H3 roughly 42 times faster and 12 times cheaper. MiniMax H3 ran at 32.3 seconds per video-second. On a 15-second product demo published on the model page, Boreal-H3 rendered in 84 seconds against 411 seconds for Seedance 2.5.

A post-training loop that learns what to improve next

Creatify details the approach in its technical report, Introducing Boreal-H3: The Next Frontier in Video Is Post-Training. The company built a closed-loop system that improves the model across data, training and inference strategy. Each generated ad is evaluated on five dimensions: brief execution, product integrity, creator identity, realism, and motion and continuity. When the feedback is unreliable, the team revises the evaluator or reward before optimizing the generator, putting measurement quality ahead of training volume.

Creatify notes that the evaluation measures ad quality before launch, and real campaign testing still has to determine which ads convert.

Pricing and availability

Boreal-H3 is available now in Creatify’s Model Playground and through the Creatify API, with text-to-video, image-to-video and reference-to-video modes. Pricing is the same across all three modes: $0.04 per second at 768p, $0.12 per second at 1088p and $0.26 per second at 2K. At 768p, that is half of MiniMax H3’s $0.08 per second list price. More details are on the Boreal-H3 model page.

About Creatify Labs

Creatify Labs is the research lab building lifelike AI video models, including the Boreal family and the avatar model Aurora. Its work centers on post-training video foundation models into production-grade generators for advertising and serving them as fast, low-cost APIs. More information is available at https://labs.creatify.ai/.

Media Contact

Yinan Na, Creatify AI, 1 (650) 319-6694, hello@creatify.ai, https://creatify.ai/

View original content to download multimedia:https://www.prweb.com/releases/creatify-labs-launches-boreal-h3-a-minimax-h3-video-model-post-trained-for-advertising-302897040.html

SOURCE Creatify AI

Continue Reading

Technology

Kindred Credit Union Partners with League Data to Modernize Banking System Operations

Published

on

By

The partnership makes Kindred League Data’s first credit union customer outside Atlantic Canada and reflects a shared commitment to sustainable modernization for Canadian credit unions and their members.

HALIFAX, NS, Oct. 2, 2026 /CNW/ — League Data announced today that Kindred Credit Union has selected the organization as its banking system technology partner, supporting Kindred’s continued modernization and its ability to serve members as their needs evolve. The partnership also marks an important milestone for League Data, with Kindred becoming its first credit union customer outside Atlantic Canada.

The partnership reflects a shared focus on building a modern and sustainable foundation for the future while preserving the cooperative values that continue to differentiate credit unions across Canada.

With over 50 years of experience supporting credit unions, League Data will work alongside Kindred to implement a cloud-based banking platform designed to simplify operations, improve integration, and support evolving member expectations.

“Modernization is about helping credit unions serve their members well today while building the capacity to adapt and grow over time,” said Chad Griffin, chief executive officer of League Data. “We’re proud to work alongside Kindred as they take this important step in their modernization journey.”

League Data’s approach to modernization is grounded in recent experience supporting coordinated transformation across the Atlantic system. Last year, League Data completed the final core banking conversion for 37 credit unions in Atlantic Canada within 15 months. Working alongside these credit unions with values-aligned technology partners like Mambu, the collaboration was able to manage complexity, share learnings, and deliver change in a practical, sustainable way.

The partnership demonstrates how the aggregation model, shaped through years of collaboration with Atlantic Canadian credit unions, can extend the benefits of shared experience, capabilities and scale to credit unions in other parts of Canada.

“Kindred sees tremendous value in credit unions working together and sharing capabilities that strengthen our system,” said Jason Daly, chief executive officer of Kindred Credit Union. “League Data brings significant experience supporting credit unions, and we’re pleased to build on that experience as we continue Kindred’s technology modernization.”

More broadly, the partnership reflects the role collaboration can play in strengthening the Canadian credit union system. By sharing experience, capabilities and scale, credit unions can address common challenges while continuing to serve their distinct members and communities.

About Kindred Credit Union

Kindred Credit Union is a member-owned financial cooperative based in southwestern Ontario. Kindred’s values-centred approach is woven into everything we do and makes us the one-of-a-kind choice for those who want to connect their values and faith with their finances. Kindred offers a complete range of banking, borrowing, and investing products and services through eight branches and online. Members benefit from access to over 43,000 surcharge-free ATMs through THE EXCHANGE® Network in Canada and the Allpoint Network in the US. To learn more about Kindred, visit kindredcu.com.

About League Data

League Data is a cooperative fintech with over 50 years of experience supporting Canadian credit unions. We provide a cloud‑native, API‑first banking ecosystem with a Canadian regulatory and payments layer, enabling credit unions to modernize at their own pace while maintaining control and independence. Our role is to simplify the complexity of technology, helping credit unions reduce costs, operate more efficiently, and deliver better member experiences while staying true to cooperative values. www.leaguedata.ca

SOURCE League Data Ltd.

Continue Reading

Technology

aosu Showcases New Doorbell Technology, SolarCam T2 and Local AI at IFA 2026

Published

on

By

Video Doorbell Ultra, faster event capture and a live aosuCortex Ultra demonstration highlight the company’s next generation of home security technology.

BERLIN, Oct. 2, 2026 /PRNewswire-PRWeb/ — aosu showcased new home security products and AI capabilities at IFA 2026 and ShowStoppers, including Video Doorbell Ultra, SolarCam T2 and a live demonstration of aosuCortex Ultra. The presentations focused on wider camera coverage, clearer detail at a distance, faster event capture and local AI processing to help homeowners understand activity around their homes.

[aosu] focused on wider camera coverage, clearer detail at a distance, faster event capture and local AI processing to help home owners understand activity around their homes.

A live look at aosuCortex Ultra at IFA 2026.

Video Doorbell Ultra combines a wider view with AI-assisted visitor communication

Video Doorbell Ultra combines 3K resolution with a wide-angle view extending almost to the sides of a doorway, covering both visitors and the surrounding entrance area. Backlight protection is designed to keep faces clearer when visitors stand against a bright sky or sunlit street.

The doorbell’s 3-in-1 detection combines PIR, radar and AI. Facial recognition, package detection and package protection provide additional information about arrivals and deliveries.

aosu also introduced plans for an AI Doorman beta, enabling the doorbell to communicate with visitors on a homeowner’s behalf. Visitors can introduce themselves, explain the purpose of their visit and leave a message. Homeowners can later review a conversation summary alongside the video.

Video Doorbell Ultra supports a removable battery and a wired power option. The product is expected to launch toward the end of 2026, with a target price of approximately $199. Final timing and pricing remain to be confirmed.

Video Doorbell Ultra on display with its wide-angle camera view at IFA 2026.

SolarCam T2 brings distant details into view

SolarCam T2 made its IFA debut with an emphasis on long-range zoom. Its demonstration showed detail at approximately 50 feet, including license-plate detail relevant to vehicles farther down a driveway. The camera’s telephoto lens captures a closer view of distant people and objects, making details easier to see across a yard or along an entrance route.

T2 also combines full-color night vision, 360° automatic tracking, Smart Vehicle Protection and local storage. Solar-powered operation and wireless installation support straightforward setup with little day-to-day maintenance.

The new model joins T2 Ultra, which emphasizes advanced night vision, and T2 Pro, which uses 3K Dual Vision to expand coverage. The lineups stated purpose is to offer options for homeowners seeking clearer nighttime views, broader coverage or more detail at a distance.

Awards on display beside SolarCam T2 at IFA 2026.

The SolarCam T2 family on display alongside the wider aosu home security ecosystem.

Separate snapshot and recording features aim to narrow the gap between solar and wired cameras

SolarCam T2 combines All Day Snapshots and Always Ready Vision (ARV), two distinct features addressing different aspects of daily monitoring.

All Day Snapshots saves a still image every five minutes, building a timeline homeowners can review as a time-lapse alongside motion recordings. The feature provides an overview of changes throughout the day, including periods between detected events, rather than continuous video.

ARV keeps an energy-saving, low-frame-rate view active between events so normal recording can begin sooner when movement is detected. This is purported to help capture more of the opening action, such as a person entering through a gate, by reducing the time spent waking the camera.

AI features simplify alerts and footage review

aosu’s showcase included people, vehicle and pet recognition, parking monitoring and smarter warnings. It also explored gun detection, dangerous-animal recognition and critical-event prioritization to help homeowners identify activity requiring attention.

Security Reports bring activity together into 24-hour summaries, while AI Smart Search helps homeowners find relevant footage using natural descriptions. Detailed AI Alerts provide information about who or what appeared, what happened and where. Live View Intelligence was is a feature with the goal of adding contextual information to the live camera view.

Exploring the aosu camera lineup at IFA 2026.

aosuCortex Ultra demonstrates local AI in action

aosuCortex Ultra operated live at the event, demonstrating real-time scene understanding, information processing and event classification. Demonstrated capabilities included person and facial recognition, re-identification (ReID) and threat detection. Processing these intelligence functions locally reduces their dependence on cloud processing.

Planned development for Cortex Ultra includes support for 24/7 recording and up to 24 devices, compared with up to eight for the current aosuCortex. The system remains at an early stage, with expanded device support and continuous recording part of its development plans.

The aosuCortex demonstration brought local AI and live camera activity together at the booth.

A closer look at the aosuCortex hardware on display.

Cortex Ultra also appeared at Qualcomm’s booth within a wider showcase of Dragonwing-powered devices. Qualcomm’s IFA 2026 Dragonwing announcements focused on bringing more AI and visual processing directly into connected products.

The Cortex Ultra display presented an AI hub combining specialized AI with a vision-language model to interpret scenes and support proactive protection. Its appearance illustrated aosu’s approach to using local processing to help home security systems recognize activity and provide homeowners with useful information about events.

aosuCortex Ultra in Qualcomm’s Dragonwing showcase at IFA 2026. The display presented its approach to local AI for home security.

Across its IFA and ShowStoppers presentations, aosu outlined a connected home security system combining broader camera visibility, faster recording response and easier footage review. The Cortex Ultra demonstration extended this direction into local AI, with development focused on helping homeowners understand events as they unfold and spend less time checking recordings.

Media Contact

Carmen, aosu, 86 15011073863, carmen@aosulife.com, https://www.aosulife.com

View original content to download multimedia:https://www.prweb.com/releases/aosu-showcases-new-doorbell-technology-solarcam-t2-and-local-ai-at-ifa-2026-302896846.html

SOURCE aosu

Continue Reading

Technology

Employer demand for tech talent reaches three-year high, CompTIA analysis finds

Published

on

By

September new job postings up 16% year over year

DOWNERS GROVE, Ill., Oct. 2, 2026 /PRNewswire/ — Employer demand for technology talent strengthened in September, increasing across a broad range of occupations, industries and skill areas, according to analysis by CompTIA.

Sixteen of the 20 industries tracked by CompTIA recorded month-over-month increases in tech job postings.

Employers posted 272,040 new openings for IT occupations in September. Active job postings climbed to 625,633, the highest total in more than three years. Compared with September 2025, new IT job postings increased 16% and active postings rose 22.4%, reflecting sustained employer demand for workers with IT skills.1

“Even in an environment where employers remain generally cautious about hiring, there is still strong demand for the core IT skills that can help companies build digital discipline and advance AI adoption,” said Seth Robinson, vice president, research, CompTIA.

Sixteen of the 20 industries tracked by CompTIA recorded month-over-month increases in tech job postings.

While demand for tech talent increased across the broader economy, employment in the technology sector declined by an estimated 10,350 positions in September, according to CompTIA’s analysis of U.S. Bureau of Labor Statistics (BLS) #JobsReport data. Tech occupation employment across all industries fell by roughly 6,000 positions. Unemployment for tech workers edged up to 3.3%, below the national rate of 4.2%.2 Over seven million individuals are employed in tech occupations.

Software, cybersecurity and data lead employer demand

Software developers and engineers remained the most sought-after technology professionals in September, with employers posting 47,598 new openings, up 8.3% from August. Systems engineers ranked second, followed by tech support specialists, data analysts and DevOps engineers. Overall, 23 of the 30 highest-volume technology occupations recorded month-over-month gains in job postings.

Active job postings requiring AI-related skills totaled 349,821, an increase of 32,327 postings from August. Since May 2024, active postings requiring AI-related skills have increased by approximately 282%. At the same time, employer demand for dedicated AI and machine learning occupations continues to grow. Active postings within CompTIA’s AI/ML job titles group reached 13,636 in September, nearly triple the level recorded in May 2024.

The “CompTIA Tech Jobs Report” is available at https://www.comptia.org/en-us/resources/research/tech-jobs-report/.

About CompTIA
CompTIA, Inc. is the leading global provider of vendor-neutral training and certification products in the information technology (IT) space. Over four million CompTIA certifications have been awarded to current and aspiring technology workers, business professionals, government and military personnel, career changers, students and others. Working in partnership with thousands of academic institutions, governments, training providers and workforce development organizations, CompTIA uses best-in-class learning solutions, industry-recognized certifications and career resources to help job seekers reach their full potential and employers develop skilled technical talent. Learn more at https://www.comptia.org/.

Contact
Steven Ostrowski
CompTIA
sostrowski@comptia.org

____________________________

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.

View original content to download multimedia:https://www.prnewswire.com/news-releases/employer-demand-for-tech-talent-reaches-three-year-high-comptia-analysis-finds-302897245.html

SOURCE CompTIA

Continue Reading

Trending