# Room Design Visualizer — Repaint, Retile and Restyle Your Own Photo > Click any wall, floor or piece of furniture in your own photo, then repaint it, remove it, or swap in a different product — all in your browser. Upload a photo of the room and click what you want to change — a scene model running on your own device has already labelled every pixel as wall, floor, ceiling, sofa, rug, curtain or lamp, so a click selects that thing exactly rather than guessing at a colour range. Then repaint it in a real paint colour, lay a tile or plank at true scale and perspective, delete it and have the background rebuilt behind it, or drop in a different product relit to the room with a contact shadow. You can also just type what you want. Nothing is uploaded. **URL:** https://convertto.tech/t/room-design-visualizer **Category:** On-Device AI (https://convertto.tech/c/local-ai-tools) **Privacy:** Runs entirely in the browser; no upload **Cost:** Free, no sign-up **Last updated:** 2026-08-01 ## Key facts - **Colour accuracy:** Exact — the hex on the swatch is the hex that is rendered - **Models:** SegFormer-B0 on ADE20K (~14 MB) labels the room; SlimSAM-77 (~40 MB) separates one item from its neighbours; RMBG-1.4 (~42 MB) only when a product photo needs cutting out - **Runs on:** WebGPU where available, WebAssembly otherwise - **Selection:** Click-to-segment on your device, plus wand and brush - **Editing:** Repaint, remove, replace — every change is an undoable layer - **Uploads:** None — the models download to you, not the photo to a server - **Privacy:** Runs entirely in your browser — nothing is uploaded - **Cost:** Free, unlimited, no sign-up ## How to use 1. Upload or paste a photograph of the room. 2. Press "Read the room" once, then click the wall, floor or object you want to change — or pick it from the list of what was found. 3. Choose a material from the catalogue, or say what you want — "deep green", "herringbone oak", "show me four modern options". 4. To change the furniture, add a product photo and press Replace, or press Remove to take something out entirely. 5. Check the before/after slider, then download the result as a PNG. ## FAQ ### Does this use AI image generation? Not for the result, and that is deliberate. Generative models drift in colour, so the same paint reference comes back a slightly different shade on each run — unusable if you are choosing an actual product. AI is used where it belongs: a segmentation model traces what you clicked. The picture itself is composited, so the colour is exact, the result is repeatable, and it renders immediately instead of queueing as a job. ### How does clicking select a whole sofa? A scene-parsing model — SegFormer trained on ADE20K, about 14 MB — labels every pixel of the photograph with one of 150 indoor classes. Clicking asks what the label is at that point and selects the whole region, so the answer is exact rather than a colour range that hopes for the best. It also means the tool can list what is in your room and let you pick from the list. Where two of the same thing touch, the Refine tool runs Segment Anything on a single click to separate them. ### What can it recognise? The ADE20K classes that occur indoors: wall, floor, ceiling, sofa, armchair, chair, stool, table, desk, bed, cabinet, wardrobe, bookcase, shelf, rug, cushion, pillow, curtain, blind, lamp, chandelier, sconce, painting, mirror, clock, vase, plant, television, refrigerator, radiator, fireplace, window and door. Anything it does not know can still be selected by hand with the wand or the brush. ### Can I remove furniture and see what is behind it? Yes. Select it and press Remove, and the background is synthesised from the surrounding surfaces using multi-scale PatchMatch — the same family of algorithm as a content-aware fill. It continues walls, skirting boards and floors reliably. It does not invent objects, so it works best on furniture standing against ordinary surfaces rather than on something covering a bookcase. ### Can I swap in a different sofa? Add a photo of the replacement. If it is a PNG with a transparent background, that edge is used as-is; anything else is cut out on your device. The old item is removed and the background rebuilt, then the new one is scaled to the footprint of what was there, corrected for the room's brightness and colour temperature, darkened slightly where it meets the floor and given a contact shadow cast away from the light in the photograph. Drag it to reposition it. ### Why does the new colour not look exactly like the swatch? Because a real camera would not record it that way either. A surface photographed under warm indoor light picks up that cast, and rendering the raw swatch colour into a warm room reads as a pasted-on layer. The "match room light" control sets how much of the room's own illuminant is applied — turn it to zero to see the pure catalogue colour. ### The selection grabbed the light switch and the skirting board. Raise "protect objects". It compares each selected pixel with the surface's own hue and releases anything too far from it, which catches sockets, switches, frames and radiators. Because it compares hue rather than brightness, the shaded half of a wall stays selected. Anything it misses can be removed with the eraser. ### Can I put a tile or a plank on at the right size? Yes. Drag the four perspective corners onto the real edges of the surface, then set its actual width in metres. Each material carries the physical size of one repeat — 300 mm for a metro tile, 1200 mm for an oak plank — so the pattern is laid at true scale and in true perspective rather than being stretched to fit. ### Are my photographs uploaded anywhere? No. The image is decoded into a canvas and every operation after that is arithmetic on pixels inside the page. The models are downloaded to your device rather than your photograph being sent to theirs, which is also why everything after the first load works offline. ## Related tools - [AI Background Remover](https://convertto.tech/t/ai-background-remover): Cut the subject out of a photo with a real segmentation model that runs in your browser. No upload, no sign-up, no watermark. - [Aspect Ratio Calculator](https://convertto.tech/t/aspect-ratio-calculator): Work out the aspect ratio of any dimensions and scale them proportionally. - [Blob Shape Generator](https://convertto.tech/t/blob-shape-generator): Design organic SVG backgrounds: four interpolation styles, gradients, layers and any canvas size. - [CSS Border Radius Generator](https://convertto.tech/t/border-radius-generator): Drag eight handles to shape every corner: elliptical radii, inverted corners and squircles. - [CSS Box Shadow Generator](https://convertto.tech/t/box-shadow-generator): Design a CSS box-shadow with live values for offset, blur, spread and colour. - [Colour Blindness Simulator](https://convertto.tech/t/color-blindness-simulator): See how a colour appears to people with protanopia, deuteranopia and tritanopia. - [Colour Converter](https://convertto.tech/t/color-converter): Convert any colour to HEX, RGB, HSL, HSV, CMYK, LAB and native code — with contrast, tints and harmonies. - [Colour Mixer & Blender](https://convertto.tech/t/color-mixer): Blend two colours and generate the intermediate steps between them.