Introducing Boreal-H3 — a video model built for ads and our next step toward recursive…
@Creatify_Labs2 тыс. подписчиков
775 273 просмотра
71 комментарий
Комментарии из оригинального поста в X (Twitter)

@Creatify_Labs
1/ One more thing about the launch video above: It was created by our researchers using our new Ad Agent, powered by Boreal-H3. Boreal-H3 gives the agent a video model optimized for the things ads actually require: product fidelity, creator consistency, directability and brief execution. Our researchers used the ad ggent to make the launch video. Now we want to see what you make with it. → Try the new Creatify Ad Agent: → Try Boreal-H3: → Technical report:
16 отметок «Нравится»

@Creatify_Labs
2/ The capability we care about most for advertising: reference fidelity. A product can’t become a slightly different product halfway through the shot. The shape, packaging, label and visual identity have to survive motion. Boreal-H3 achieves 85.3% reference fidelity — the highest among the frontier video generation models we evaluated. Look closely at the product↓
14 отметок «Нравится»

@Creatify_Labs
3/ But an ad is more than one faithful frame. The model also has to follow the actual creative brief across shots, actions and transitions. For example: cliff jump → wingsuit flight → beach landing → vendor → final bite. Boreal-H3 completes the full sequence. Following the brief means reaching the payoff.
15 отметок «Нравится»

@Creatify_Labs
4/ The visual examples show the difference. The evaluation tells the same story. → 85.3% reference fidelity — highest among the frontier models evaluated → 133.3 Ads Quality index — highest observed across six frontier models Ads Quality jointly measures reference consistency, prompt following and visual realism. We optimize for whether a generation is actually usable as an ad—not just whether it looks good.
17 отметок «Нравится»

@Creatify_Labs
5/ So what did we actually change? This is not a one-off SFT or LoRA fine-tune. Our post-training system closes the loop: real-use feedback → capability diagnosis → choose what to improve → data / training / inference intervention → evaluate against the incumbent → record the result → repeat SFT and RL are tools inside the loop—not the whole recipe.
13 отметок «Нравится»

@Creatify_Labs
6/ A concrete example: If the model starts drifting on product packaging, the answer isn’t simply “train more.” The system can identify the failure, collect more packaging and product-handling data, curate it, train a new candidate, and test whether fidelity improves without regressing elsewhere. And if the evaluator itself is noisy, we fix the evaluator first. Every experiment becomes memory for the next intervention. That’s what we mean by toward recursive self-improvement in video generation.
12 отметок «Нравится»

@Creatify_Labs
Try Boreal-H3: Try Ad Agent:
14 отметок «Нравится»

@JayminSOfficial
Reference fidelity and brief success are exactly the metrics that turn video models from impressive demos into usable ad infrastructure!
15 отметок «Нравится»

@Creatify_Labs
Exactly. A demo can look great and still be useless for an ad. Those are the numbers that matter.
2 отметки «Нравится»

@TiffanyFong
Insane 🔥
7 отметок «Нравится»

@Creatify_Labs
Thanks Tiffany! 🙌

@ElonMuskAOC
It’s getting too easy now!
6 отметок «Нравится»

@Creatify_Labs
That's kind of the point 😄
3 отметки «Нравится»

@pmitu
wow what a movie check my result:
6 отметок «Нравится»

@Creatify_Labs
In one shot is wild, Paul. The UI stayed clean all the way through. Love this!
2 отметки «Нравится»

@testingcatalog
Quality / price ratio is at peak 💪👀
3 отметки «Нравится»

@Creatify_Labs
Indeed! We offer the best quality / price for ads for sure!
1 отметка «Нравится»

@elong_tusks
no one absolutely no one gives a fuck 🖕🏼🤣
3 отметки «Нравится»

@antinertia
love it! how long did it take to build this new version?
3 отметки «Нравится»

@Creatify_Labs
Thanks! The feedback loop behind it was months of work, and it keeps improving the model from here.
2 отметки «Нравится»


























