cd /news/generative-ai/how-room-repaints-work-on-swatcher · home › topics › generative-ai › article
[ARTICLE · art-172255] src=tj.ie ↗ pub= topic=generative-ai verified=true sentiment=↑ positive

How room repaints work on Swatcher

Swatcher.ie launched a room-repaint experiment that wraps a single OpenAI image-model call, made through the Laravel AI SDK, in a queued Laravel job that pins each result to a named paint by brand and exact hex, such as Farrow & Ball's "Studio Green" at #464d4b. The service centre-crops uploads to the model's three supported shapes (square, 3:2 and 2:3) before saving, strips metadata including EXIF location, and measures every result's colour drift, reporting the wall as close under about 3 and near up to 6. Failed repaints are never charged, credits are held during the run and spent only after the result is written to disk, and the first 3 repaints are free.

recommendation

Measure each generated image's colour against the requested hex and only claim a match under about 3; hold credits during the run and charge only after the result is written to disk.

more in playbook: Verifying model output
by read3 min views2 publishedNov 11, 2026

The room visualiser I built earlier uses stock rooms rendered in Blender and recolours them in the browser with plain colour maths. I’d ruled out generative models for it: they guess, and a paint tool that guesses is a bad paint tool. But I think people kept want their room, not mine. So I built repaints as an experiment, and spent most of the effort on the parts around the model: pinning it to a real paint, measuring how far it drifts, and never charging for a miss.

If a repaint fails, nothing is charged and you get a short reason: the model declined the photo, the service was busy, or it just didn’t work. It’s a Laravel app, so a repaint is a queued job wrapped around one image-model call to OpenAI through the Laravel AI SDK. Four parts do the real work.

The image model only returns three shapes: square, 3:2 and 2:3. On upload I resize the photo, strip its metadata (including EXIF location), and centre-crop it to whichever of those shapes is nearest. It’s cropped before it’s saved, so the original I keep and the picture the model returns are exactly the same shape. That’s what lets the slider line them up, and the colour check compare them pixel for pixel.

Left alone, an image model “improves” the whole picture. It brightens the window, tidies the sofa, nudges the camera. So the prompt is deliberately bossy. It names the paint by name, brand and exact hex, for example “Studio Green” by Farrow & Ball, exact colour #464d4b, and asks for that hex as it would be lit in this photo, not a similar shade.

Then it lists what must not change: lighting, shadows, reflections, wall texture, furniture, floor, ceiling, windows, artwork, people, perspective, framing. With no trim paint chosen, the trim is on that list too.

A model asked for #464d4b won’t always paint #464d4b. I don’t want to hide that, so every result is measured.

Under about 3, most people can’t tell two colours apart, and the page says the wall came out close to the paint. Up to 6, it says near. Past that, it says nothing rather than make a claim it can’t back up. Some gap is expected even from a perfect repaint, because a wall in shadow is genuinely darker than the chip.

Credits are held while a repaint runs and spent only once a result is safely written to disk. A worker claims each repaint with a conditional update, so two workers can never run it twice. The charge happens under a lock on both the account and the repaint, because the model call can take minutes and the person might have deleted it in the meantime. A scheduled command fails anything stuck too long, and none of these paths can overwrite a repaint that already succeeded and was paid for.

The obvious next step is a hybrid: let the model find the walls, then let the visualiser’s colour maths set the exact paint. I’m holding off until I see how people actually use it.

Sign up at swatcher.ie, open the visualiser and choose “Your own room”. The first 3 repaints are free. If it gets a colour badly wrong, I’d love to see the photo and the paint you picked. Those cases are what will decide whether the hybrid gets built.

── more in #generative-ai 4 stories · sorted by recency
── more on @swatcher 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/how-room-repaints-wo…] indexed:0 read:3min 2026-11-11 · —