Avoxkit · Image repair · Watermarks and logos

Image repair,
find it, paint it, fill it.

Remove watermarks, channel logos and overlay text from your own material and let a model fill the background back in: automatic detection when positions vary, manual painting when you know the spot. JPG, PNG, BMP and WebP, whole-folder batches, everything on this machine.

  • JPG / PNG / BMP / WebP
  • Automatic detection + manual painting
  • Free · local
Avoxkit image-repair page: automatic and manual modes, output format and model status

How it works

Two roads, depending on the watermark

Detection and inpainting run as a relay: first find what to remove, then fill the background back.

Automatic detection

A model first flags likely watermark positions, then the background is filled back in. Fits images where watermark positions vary; folder batches always run automatic.

LaMa + YOLO26-Seg · model ~290 MB on demand

Manual painting

Paint over the logo or text on the preview and only painted areas are repaired. Fits logos and overlays at known positions — you decide the boundary.

Smaller painted areas inpaint better

Before / After

The painted area is filled back in

Manual mode in this example: only the watermark is painted on the preview; the rest of the pixels stay untouched.

Before repair: a red heart watermark on a mountain meadow
Before
After repair: the heart is gone and the grass and scree are filled in by the model
After

Free

Repair costs nothing, with no count limits and no watermark on output.

Local

Detection and repair run on this machine; images are never uploaded.

Batch

Queue whole folders, all through automatic detection, failed items retry in one click.

Limits

Edges, stated up front

Inpainting is generated, not recovered.It does not guarantee a match with the original background, especially on large areas; keep the original of anything important.

Output keeps the input format.JPG carries a slight loss; pick PNG when you will keep editing.

Re-running overwrites the same -repaired file.Rename first if you want to keep several versions.

Only for images you have the rights to.This feature is for your own material: logos, watermarks and text on your own screenshots and photos.

Get

Three steps

Current release 0.2.0 for Windows 64-bit and macOS (Apple Silicon), entirely free.

  1. Open an image or a whole folder.
  2. Pick automatic detection, or switch to manual painting and mark the area.
  3. Start; output is a same-named -repaired file.

Download from GitHub Releases, or see the Avoxkit home page.

Requirements

  • Windows 64-bit; macOS (Apple Silicon)
  • Detection and repair models download on first use, ~290 MB, checksummed
  • Repair runs fully offline; images never touch the network

Detection runs on YOLO26-Seg and inpainting on LaMa; the interface is provided through the open-source engine avox, UI built with Flutter. Avoxkit is AGPL open source on GitHub.

FAQ

Does the repaired background match the original?

Not guaranteed. Repair is generated inpainting, especially on large areas; keep the original of anything important.

Automatic or manual?

Positions vary or there are many: automatic detection finds them first. A logo or text at a known spot: manual painting, which only touches painted areas.

Which formats?

JPG, PNG, BMP and WebP, whole-folder batches; output keeps the input format by default, JPG with a slight loss — pick PNG to keep editing.

Does the model download?

On first use, about 290 MB with SHA-256 verification, only when you need it. Detection and repair run on this machine; images are never uploaded.