What is MeituHub

MeituHub is the AI imaging platform from Meitu. It turns the image-and-video AI that Meitu has built up over the past 15 years into a set of callable building blocks, so creators, teams, and developers can produce images, video, audio, and motion content without standing up their own AI stack.

Think of each AI capability as a building block. You can use one on its own, or chain several together into an automated pipeline that cranks out finished visuals in bulk.

The one-line pitch: bring Meitu's full AI imaging stack to your own product or workflow — no AI infrastructure required.

Who it's for

WhoWhat they do with MeituHub
CreatorsGenerate images, video, and motion from plain language — no code, no fiddly setup
Business & operations teamsBuild a reusable pipeline once ("cutout → swap background → add copy → batch export") and reuse it forever
Developers & engineering teamsCall image and video AI over CLI or REST API and wire it into your product, scripts, and CI pipeline

Core capabilities

MeituHub covers the full imaging stack — images, video, audio, and motion:

CategoryHighlightsTypical use cases
Image generationText to image, poster design, AI portraits, ID photos, product multi-angle shotsBrand visuals, e-commerce main images, personal photos
Image editingCutout, background replace, object removal, text replace, style transfer, face swapProduct retouching, photo polish, creative design
Image enhancementSuper-resolution upscale, low-light lift, denoiseOld-photo restoration, quality boost, print-ready assets
Video generationText to video, image to video, multimodal generation, video effectsPromo clips, product demos, animation
Video editingContent replace, object removal, canvas expand, logo overlayRemixing, brand placement, multi-platform adaptation
Video enhancementQuality boost, resolution upscale, denoise, low-light lift, frame-rate upgradeVideo repair, HD conversion, streaming assets
Audio generationBGM generation, full song generationVideo scoring, brand atmosphere, mood setting
Motion generationMotion transfer (dance-to-video), video to GIFVirtual idols, short dance clips, stickers

Key concepts

  • Workflow — a visual canvas where you chain multiple AI capabilities into one automated pipeline. Configure once, reuse as often as you like, run in batch.
  • Capability — a single, callable AI skill on the platform, such as smart cutout or text-to-video. When you publish a Workflow, it becomes a reusable Capability.
  • Credits — the platform's shared billing unit. Each capability consumes a different amount: image capabilities are billed per request, video capabilities per second.

Three ways to use it

WayWhat it isBest for
CLIInstall via npm and call from the terminal; supports JSON output and scriptingDevelopers, engineering teams, CI/CD pipelines
APIGrab an API Key and call any image or video capability over HTTP; integrate per the API docsBack-end developers, enterprise systems
Chat to WorkflowDescribe what you want in natural language; the AI agent assembles the nodes on the canvas and runs it. Publish the result as a reusable capabilityCreators, business teams, non-technical users

By industry

MeituHub ships pre-built workflow templates and custom builds for four leading industries:

IndustryTypical scenarios
E-commerceBatch product-main-image / detail-page generation, smart cutout, background replace, unified brand visuals
GamingCharacter concept art, three-view sheets, multi-style output, batch 2D asset production
EducationBatch course-slide illustrations, auto-generated micro-lecture videos (with voice & subtitles)
MarketingCreative video generation, auto multi-platform sizing, batch marketing asset output