Back to the map

How this map was drawn

This is Pleasanton, California as one continuous isometric drawing, about 8,500 tiles of it. A model drew every tile from a 3D view of the real place. Most of the work was making the tiles join, and catching the model when it drew something that is not there.

The map has been drawn twice, in two different ways. Both are on the site: use the selector at the bottom of the map to switch.

The fairgrounds pond in v1: the pond and the grass change shade along straight lines where four windows meet. The same pond in v2: one continuous drawing with no straight edges. v1v2
The pond inside the fairgrounds racetrack, drawn both ways. Drag the divider. In v1 four separately drawn windows meet in the water and each chose its own blue. In v2 the whole neighbourhood was drawn at once.

From a 3D model to a drawing

  1. Render. Every 130 m block of the city, 2,353 of them, was rendered from Google's photorealistic 3D tiles with one fixed camera: looking southeast, 30 degrees down. The renders are only an input and are never published.
  2. Make examples. An image model redrew 100 sample blocks in one illustration style. Each result was checked by hand against its render, and 238 were kept as training pairs.
  3. Teach the style. A LoRA, a small add-on trained for about two hours on those pairs, makes the open image-editing model Qwen-Image-Edit redraw any block in that style while keeping every street, building and tree where it is.
  4. Draw the city. The model draws one block-sized window at a time, and a city is thousands of windows. The two versions differ in how the windows are made to join. That is the next section.
  5. Check against the real thing. Every tile is compared with its render. Where the drawing does not follow the render, the tile is redrawn or held back.
  6. Publish. The tiles are stacked into nine zoom levels and served as plain files. The land around the city is public aerial imagery, tilted to the same camera and covered in mist.

Two ways to draw a city

A window on its own comes out well. The hard part is the edge between two windows: left alone, each one picks its own shade of grass, its own blue for water, even its own idea of whether a track is sand or asphalt.

v1Window by window

drawn first drawn first drawn next, both at once

Six tiles in a row. The edge in the middle was seen by neither of the two later windows.

Each window is drawn next to finished neighbours. The model is shown the art that already exists on some sides and fills in the rest, so roads and roofs carry on across the edge.

To finish in hours instead of days, windows that do not overlap are drawn at the same time on several GPUs. That is where it breaks: two windows drawn at the same time can share an edge that neither of them saw. On even ground such as a golf course, the map shows squares.

The repair came afterwards. Every tile's colours were pulled toward what its render implies, which evens out the tone. It cannot make two windows agree on what a surface is.

v2Drawn together

held averaged averaged one neighbourhood, one picture

Solid: the windows of one step. Dashed: where they sit on the next step. The green strip is a finished neighbour, held in place.

The model does not draw in one go. It starts from noise and refines the picture over 16 steps. v2 treats a whole neighbourhood, about a kilometre across, as one picture. At every step the model looks through many overlapping windows, the predictions are averaged where windows overlap, and the next step starts from that shared result.

No window ever finishes on its own, so there is no edge to hide. On every other step the windows move over by half their spacing, so no spot always sits at the rim of a window.

Neighbourhoods are drawn in four rounds. A later one begins with a strip of its finished neighbours held in place, so it grows out of them. The model and the style add-on are the same as in v1: nothing was retrained.

Downtown Pleasanton in v1: flat roofs and simple trees, with faint straight edges between windows. Downtown Pleasanton in v2: more roof, window and tree detail and no straight edges. v1v2
Downtown. Drawing a neighbourhood at once also kept more of what is really there: brick fronts, roof equipment, the shapes of individual trees.

Empty ground, and what the model put on it

Drawn together, the neighbourhoods came out better than in v1. Open land did not. Where the 3D view shows only dry grass, vines or plowed soil, the model has little to hold on to, and it fills the space. The first pass of v2 drew a subdivision into a vineyard, a small town into a plowed field and compounds onto bare hills. A check that compares every tile with the 3D view found something that is not there in 429 of the first 5,464 tiles, nearly all of them on open land. That pass was stopped two thirds of the way through.

A vineyard in the first pass of v2: a grid of streets and houses drawn into the middle of the vines. The same vineyard in v2 as published: rows of vines, a dirt road, no houses. first passv2
A vineyard on the east side of town. The first pass started from noise and drew houses that do not exist. The published v2 starts open land from the broad shapes of the 3D view.

Asking again with a different random start does not help: the model invents something else. What helps is not starting from nothing. On open land, for the first six of its sixteen steps, v2 pulls the broad shapes and colours of the picture toward the 3D view of the place. Only shapes wider than a house are held. Everything finer is left to the model, so the lines are still its own. After the sixth step it is let go and finishes the drawing by itself.

The sixteen steps of one drawing. Filled: open land is held to the broad shapes of the 3D view. Empty: the model draws alone.

Three simpler ideas failed first, and each failure said something about the model. Given a blurred picture of the ground to start from, it handed back the blur. Given the sharp 3D view, it returned a lightly painted photo: correct, and no longer a drawing. Holding only the broad shapes kept both the place and the drawing.

Neighbourhoods still start from noise, because that is where the model draws its crispest lines and because it does not invent where there is a street to follow. Open land is 36% of the map.

The rule that says what is open land was wrong once. The oak woods on the hills west of town photograph blue, the rule took blue-green for built-up ground, and 597 tiles of forest were drawn from noise. The model put a manor, a church and a small subdivision under the trees. Drawn again with the pull, the forest is a forest.

Oak woods as first drawn in v2, from noise: walled compounds of tiled roofs stand among the trees. The same woods in v2 as published: unbroken tree crowns and a few dirt clearings. from noisev2
Oak woods west of town. Taken for built-up ground, they were drawn from noise and filled with buildings. With the pull they are trees again.

The two runs in numbers

v1v2
Drawn in one pieceone window, 130 m acrossone neighbourhood, about 1 km across
Pieces4,176 windows53 neighbourhoods
GPU time13 hours20 hours
On three rented GPUs4.5 hours, $438.5 hours, $78
Tiles drawn again after the checks18776
Tile edges with a visible step, fairgrounds area73%1%
Starts fromnoise, beside finished neighboursnoise in neighbourhoods, the 3D view's broad shapes on open land
Tiles the edge check flags51 of 8,47122 of 8,474
Passes thrown awaynoneone, stopped at two thirds ($36)

What the model got wrong

Built with

Credits