Skip to content
QGIS plus AI

What AI can do inside QGIS, and what it cannot

One plugin turns your imagery into vectors. The other turns it into different imagery. Both run on any laptop with no GPU, and clicking one object at a time on your own machine is free, with no counter.

Install free in QGIS

QGIS 3.22 or later. Windows, macOS, Linux. No GPU, no Python setup, no card.

The short answer

AI in QGIS does two jobs today.

AI Segmentation reads imagery and returns the objects in it as polygons. AI Edit draws a new map on that imagery from a written instruction. Both run without a GPU. Neither plans your project, checks your attribute rules or replaces a field survey.

Runs in
QGIS 3.22 and later
Starts at
Free, no card
0:00 / 0:00
AI SegmentationRead it

Every object, as a polygon

Click an object and get its outline. Or name what you want ("buildings", "solar panels", "trees") and get every match across an area, as an editable layer in your project CRS.

Output: a polygon layerSee AI Segmentation
0:00 / 0:00
AI EditChange it

A new raster, same coordinates

Select an area, describe the change in plain words, and get imagery back that no longer shows the clouds, the cars or the winter. It lands aligned to the same extent and CRS.

Output: a georeferenced rasterSee AI Edit

Why these exist

The slow parts of a GIS job

Neither plugin invents new work. Both take something you already do by hand and make it quick.

Someone has to draw the map

Every building, every field, every tree starts as a person clicking corner after corner. On a real site that runs to days, and the layer is stale before it ships.

The imagery is never the one you need

Cloud sits over the site. The flight was in January and the report is about summer. The car park is full and you wanted the surface. The tile is 50 cm and the print is A1.

And the fix used to need a GPU

Models this good want a dedicated graphics card, CUDA and a Python environment. GIS work happens on a work laptop. So the model runs on our servers, and QGIS just asks it for the answer.

Which one

Find your job, get your plugin

The two do different work. Find the task you came here for.

AI Segmentation
  • Get building footprints as polygons
  • Extract a road network from aerial imagery
  • Map individual tree crowns
  • Count solar panels across a district
  • Digitize water bodies or field boundaries
  • Trace one awkward object without clicking every corner
AI Edit
  • Remove clouds from a scene you need to present
  • Clear the cars off a car park to see the surface
  • Show a site in summer when your orthophoto is from January
  • Preview a development or a flood extent on real ground
  • Sharpen a low-resolution tile for print

Need both? The Pack covers the two plugins on one subscription. See pricing

Real runs

What comes back

Output from real runs in QGIS, one block per plugin.

AI Segmentation

Detection results as they land in the project. Every object gets its own colour, which is how the layer looks before you export it.

Dense Parisian city blocks, each detected block filled with its own colour

City blocks

Central Paris. One pass returned 635 polygons.

Individual tree crowns around a lake, each crown filled with its own colour

Tree crowns

Parkland around a lake. One pass returned 925 polygons.

Cars parked along city streets, each car outlined in its own colour

Parked cars

Street parking across a district. One pass returned 575 polygons.

AI Edit

Imagery edits, one prompt each. Drag the handle to compare. Every result comes back on the extent and CRS of the tile that went in.

A harbour front before and after the water level is raised over the quays (after)
A harbour front before and after the water level is raised over the quays (before)
BeforeAfter
Drag to compare

Raise the water

The quays and the square go under. Only the tree crowns stay above the line.

A residential street before and after solar panels are added to the roofs (after)
A residential street before and after solar panels are added to the roofs (before)
BeforeAfter
Drag to compare

Panels on every roof

A residential street fitted out, to show a scheme before anyone builds it.

A suburban tile before and after upscaling, with sharper roofs and hedges (after)
A suburban tile before and after upscaling, with sharper roofs and hedges (before)
BeforeAfter
Drag to compare

Sharpen for print

A soft tile resolved for A1. The model invents the fine detail, so read it as a picture, not as evidence.

Getting started

Running in about a minute

1

Install from the plugin manager

In QGIS, open Plugins, then Manage and Install Plugins. Search the plugin name and click Install. No admin rights needed.

2

Sign in once

Open the panel and sign in with your email. No card. The free tier starts immediately and your key works on every machine you use.

3

Load a raster and run

Any raster works: a GeoTIFF on disk, an XYZ basemap, a WMS layer. What is on screen is what the plugin reads.

Questions people ask before installing

  • Yes. TerraLab ships QGIS plugins for imagery and map work. AI Segmentation detects objects in imagery and returns them as vector polygons: draw an area, name the object, get every instance. AI Edit changes what the imagery shows from a plain-language instruction. AI Agent runs tasks in the project you have open. Geo-SAM, GeoOSAM, SamGIS, Bunting Labs and Mapflow are other options, and three of them are free.
  • There is a free tier with no card. Clicking an object and getting its outline costs nothing when the model runs on your own machine, with no counter. Automatic detection across an area, the same click answered by our best model, and imagery edits use a monthly allowance that resets. Paid plans start when that allowance runs short. For scale, a paid plan costs about twenty minutes of billable consulting time a month, or roughly one percent of a commercial GIS seat.
  • No. The heavy models run on our servers, so a standard work laptop is enough. The click-to-segment model also runs on a plain CPU when you keep it on your own machine. This matters more than it sounds: the newest Segment Anything release needs a graphics card with CUDA and has no CPU path, which rules out every Mac and every machine on integrated graphics.
  • Yes. Anything QGIS can load as a raster works: satellite scenes, aerial orthophotos, drone flights, scanned maps, XYZ basemaps and WMS layers. Detection quality tracks ground resolution more than the source, so a sharp drone orthophoto usually gives the best results.
  • GeoAI is the use of machine learning on geographic data: satellite and aerial imagery, point clouds, vector layers. In practice it means models that read a map the way an analyst would, finding objects and patterns. Running it inside QGIS is what turns it from a research topic into a working tool.
  • It is stored on our servers in Europe, and AI Segmentation runs its detection there too. AI Edit sends what you select to an AI provider that may process it outside the European Union. We do not train any model on it and we do not share it. If you prefer, click-to-segment runs on your own machine, and then nothing leaves your computer. You can ask us to delete everything at any time.
  • No plugin can give you one honest number, because it moves with your imagery and with what you extract. Expect a first pass you review, not a finished layer. Our plugin opens every run in a review step where you filter by confidence, add what was missed and delete what is wrong. Test it on your own imagery before you trust anyone's figure.