HiAPI
creatify-boreal 详情页 Hero 图:21:9 宽幅,左侧柔光留白,右侧半透明胶片带与玻璃轨道浮卡交织,暖奶油底映冰蓝与珊瑚粉,发光立体字构成片名。

Creatify

Creatify Boreal

creatify-boreal

A low-cost video generation model for batch variants of ad creatives, supporting text-to-video, image-to-video, and photo-plus-audio generation of multilingual talking videos, with fast output

creatify-boreal

Try creatify-boreal

Input

Output

video
Fill in the parameters and run — results show up here.

Pricing

creatify-boreal per second

Specifications Unit Price
720P $0.0145
1080P $0.043
2K $0.1715

Positioning Overview

creatify-boreal is a general-purpose video generation model for advertising and short-form video assets, supporting text, image, and audio input paths to generate video. It writes visuals, dialogue, sound effects, and on-screen text uniformly into the prompt, and can drive the final output based on reference images or audio, producing clips from 720p to 2k and 1 to 20 seconds. It is suited for developers and marketing teams that need low-cost, rapid production of multiple video variants for creative testing, rather than scenarios pursuing complex storyboarding and high-precision product shots.

Core Highlights

  • Three input paths, covered by one API — The same model can initiate generation with a prompt, reference image, or driving audio, reducing the cost of switching models for different asset formats.
  • Controllable duration and resolution for easy batch planning — Duration is set in whole seconds from 1 to 20 seconds, and output can be 720p, 1080p, or 2k, making it easy to standardize specs across delivery channels.
  • Supports audio-driven and talking-head visuals — Passing in narration or dialogue audio drives the visuals, taking the leading segment according to the requested duration and filling in silence when the audio is insufficient.

Capability Description

Structured multimodal prompting: The prompt can be described in four parts—visuals, dialogue, sound effects, and on-screen text—with a limit of 5000 characters per prompt, controlling both picture and sound content in a single generation.

Reference image and aspect ratio control: A reference image can be passed in as the animation starting point; when the aspect ratio is left as auto, it follows the image's proportions, and when 16:9, 9:16, 1:1, 4:3, or 3:4 is specified, the output is center-cropped.

Tiered resolution output: Choose 720p, 1080p, or 2k output tiers based on delivery needs, adapting to clarity requirements from quick previews to formal delivery.

Exclusions and AI labeling: Negative prompts can be used to exclude unwanted content or visual defects, and an optional visible AI-generated label can be overlaid on the final video.

Use Cases

  • Batch ad asset variants for marketing teams — Generate multiple short videos with different expressions from the same creative direction, producing assets that can go directly into delivery testing.
  • Product image to video for e-commerce teams — Initiate generation with a product or product image as the reference image to obtain usable dynamic showcase clips for product pages and feeds.
  • Talking-head and explainer videos for content teams — Provide narration or dialogue audio together with visual descriptions to produce well-paced explainer clips for social media short-video distribution.
  • Low-cost concept test shoots for creatives — Quickly validate multiple creative directions with text, see the results first, and then decide whether to invest in a more refined production process.

Limitations and Selection Advice

Positioned as a fast, low-cost exploratory-tier model: control over complex narratives, key product shots, and multi-reference-shot final output is limited, and such needs are better served by higher-precision models in the same series. Most currently available public information comes from vendor self-descriptions and lacks independently verifiable benchmarks, so model selection should be based on actual testing with your own assets. Prompts are recommended to use structured English phrasing, and the effectiveness of long Chinese descriptions should be verified yourself. Billing is based on requested duration, so longer durations cost more; during the test-shoot stage, it is recommended to start with short durations.

  • Price update creatify-boreal Price Adjustment Announcement
  • Parameter change creatify-boreal: the optional manifest_disclosure parameter…
  • New model New model: creatify-boreal

Frequently asked questions

View all FAQs →
  • What inputs does Creatify Boreal accept?

    A prompt is required; one reference image and one driving audio file are optional. Use the prompt alone or combine all three.

  • How should I write the prompt?

    Use four sections: [VISUAL] for the shot and camera, [SPEECH] for the line, [SOUNDS] for effects and music and [TEXT] for on-screen text. Write None for sections you do not need.

  • Does it support languages other than English?

    English prompts give the steadiest results today; other languages are not guaranteed, so start in English.

  • How long can a video be?

    1 to 20 whole seconds, 10 by default.

Related Models

View all models →

Same Type