Lompat ke konten
KaiConvert
AI lokalDirencanakan

Remove the background from an image

Planned as a local AI tool: segmentation running on your own device, not on a server.

Belum tersedia

Alat ini masih dalam peta jalan. Halaman ini ada untuk mendokumentasikan alurnya, formatnya, dan alat terkait — tetapi tidak ada yang diproses dan tidak ada hasil yang dibuat.

AI lokal
Lihat alat yang sudah berfungsi

This page has not been translated yet and is shown in English. It is excluded from search indexing for this language until it has been.

Background removal is the single most requested image operation on the web, and it is also the one most commonly implemented by uploading your photo to somebody else’s GPU. KaiConvert’s plan is different: run the segmentation model in your browser through ONNX Runtime Web, using WebGPU where the device supports it and WebAssembly where it does not.

That design is why the tool is not shipping yet. A usable segmentation model is tens of megabytes, needs to be lazy-loaded, warmed up and run inside a Web Worker so the page stays responsive, and needs a graceful path on devices that can do none of that. Shipping a fake version in the meantime would be worse than shipping nothing.

Apa yang Anda dapat

  • On-device inference is the goal

    The model runs in your browser, so the photo never needs to be uploaded to be segmented.

  • WebGPU with a WASM fallback

    Accelerated where the hardware allows, still functional where it does not, disabled with a clear message where neither works.

  • Feeds straight into the editor

    A cut-out is rarely the end of the job. The result will land in the same canvas as crop, resize and export.

Cara kerjanya

  1. 1

    Capability detection

    KaiConvert checks for WebGPU, WebAssembly, OffscreenCanvas and available memory before offering the feature.

  2. 2

    Lazy model load

    The segmentation model is fetched only when you actually use the tool, then cached by the browser.

  3. 3

    Worker inference

    Inference runs in a Web Worker so the interface stays responsive, and the mask is composited onto the canvas.

Spesifikasi

  • This tool is not implemented yet. Nothing is processed, no image is uploaded, and no result is produced. The page documents the intended workflow and is excluded from search indexing until the feature actually works.
  • Planned as Tier B (local AI): ONNX Runtime Web, WebGPU with a WebAssembly fallback, inference in a Web Worker.

Mengapa memakai KaiConvert

  • Tanpa unggah untuk alat lokal
  • Tetap berfungsi luring setelah halaman dimuat
  • AI awan selalu diberi label jelas sebelum Anda mulai

Pertanyaan umum

Alat terkait