Creatify Labs launches Boreal-H3, a MiniMax H3 video model post-trained for advertising
PR Newswire
MOUNTAIN VIEW, Calif., Oct. 2, 2026
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
