Removing the background from an image — local first, AI for tricky edges

Design Studio has a one-click background remover on every image you place on the canvas. Two modes — local (free) and AI refine (~1¢) — so you only pay for the edge cases that actually need it.

To use:
1. Click the image on the canvas to select it.
2. The right-rail Properties panel shows "Remove background" near the bottom of the image controls.
3. Click "Remove background" — the local model runs and swaps your image in place with a transparent-PNG version. Usually 2–10 seconds depending on size.
4. If the cutout looks great, you're done. If hair, fur, or translucent edges look rough, click the smaller "Edges look off? Refine with AI (~1¢)" link below.

Local mode (default — free, in-browser):
• The cutout itself runs entirely on your device. Your photo is never uploaded and there is no charge to your org.
• The first time you use it, your browser downloads about 110 MB of model and runtime files from the tool that powers it (img.ly's CDN). Your photo is not part of that — only the model comes down. We ask before starting the download and show its progress.
• Your browser may need to download those files again on a later visit, so this is not always a one-time cost. On a metered or slow connection, use AI refine instead.
• Not offered on the Turtini mobile app, on devices with limited memory, or when your browser is set to reduce data use — the download is too large to start there. Those devices get the AI option instead.
• Where your browser supports WebGPU, the work runs on the graphics card and off the main thread, so the editor stays responsive. Without WebGPU it runs on the processor and the editor will pause while it works.
• Works well on most photos with clear subject/background separation (products, people, vehicles)
• Trades off a bit on very fine edges (loose hair, fur, smoke, fluffy fabric)

AI refine mode (~1¢):
• Calls Replicate Bria-RMBG (a model tuned for tricky edges)
• Better on hair, fur, translucent edges, fabric details, complex backgrounds
• Result is a fresh transparent PNG that swaps into the canvas same as local mode
• Charges roll up to orgs/{orgId}/usage at +15% — the title text on the button shows the rough cost so you're never surprised
• Use sparingly — most images only need local mode

Both modes preserve your filters:
Brightness/contrast/saturation/blur applied before the background remove are reapplied to the new transparent image, so your color treatments survive the cutout.

Re-running:
You can re-run either mode on the same image — each run starts from the current canvas image, so you can stack edits (e.g. local-cutout then AI-refine if local missed an area). Every cutout is saved to your asset library first, which is what lets the AI step read it and what keeps the result after you close the design.

Undo:
Cmd/Ctrl+Z undoes the cutout and brings back the original image. The history stack pushes a step on every successful run, so you can always step back.

If it fails:
• "Failed to load processed image" — usually a network blip on the AI mode; try again, or switch to local mode
• Local model takes too long — the first run includes the ~110 MB download; after that, a very large image is the usual cause, so resize on the canvas before running (smaller image = faster cutout)
• Edges still look off after AI mode — the source image may have such soft separation that no model can recover it cleanly. Try cropping tighter around the subject before running.