AI Inpainting
Commercial use OK
380+ models
No watermark
No sign-up needed
Model:
+ GPT-5, Claude, Gemini
Paint over the area you want to change — an object to remove, a face to fix, a sky to swap. Then describe what should fill the painted area. Works on JPG / PNG / WebP up to 10MB.
Advanced options
Result
Tokens running low.
Get More Tokens
❤️ Love Free.ai? Tell your friends!
Sign up to get a referral link and earn 25,000 tokens per friend.
Want more?
Sign up free for 5K tokens/day + 10K bonus
Sign Up Free
Processing your request...
Fill in or replace parts of images with free AI inpainting. Edit photos seamlessly.
How to Use AI Inpainting
1
Enter your input
Type text, upload a file, or describe what you want. No account needed.
2
Click generate
Our AI processes your request in seconds using the best open-source models.
3
Download & share
Download, copy, or share your result. Free for personal and commercial use.
Use this tool via API
Automate this tool from your own code. OpenAI-compatible REST endpoint, Bearer-token auth, no extra SDK required. Token costs match the web interface.
curl -X POST https://api.free.ai/v1/image/generate/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"prompt": "A sunset over mountains", "model": "sdxl"}'AI Inpainting — FAQ
Paint a mask over any part of an image, then describe what should fill that area. The AI regenerates only the painted pixels and leaves everything outside the mask pixel-perfect. Works for object removal, sky replacement, adding elements, fixing imperfections, and content swaps.
After uploading, click and drag on the canvas to paint. The red overlay shows what will be regenerated. Use the brush-size slider, the eraser to refine edges, Invert to flip the selection, and Clear to start over. Touch + mouse both work.
No — if you don't paint anything we fall back to the Area Selection picker (auto-detect from prompt / foreground / background / faces only). Painting a mask is always more precise, especially for removal and complex scenes.
Standard (Stable Diffusion XL inpaint) runs on our GPUs and uses your free daily pool. Kontext Pro (premium) preserves identity and lighting better — best for faces and text. Seedream 4 Edit (premium) produces the cleanest detail recovery on complex backgrounds.
Standard costs 1,000 tokens per inpaint. Kontext Pro costs ~30,000. Seedream 4 Edit costs ~70,000. Signed-up users get 5,000 free tokens/day — enough for multiple Standard inpaints daily. Buy more for premium.
Describe what should fill the painted area. Short and literal works best: "clear blue sky," "grass matching the rest of the lawn," "a vintage brass lamp," "remove completely and match the background." Verbose prompts confuse the model.
The editor is prompt-only: you describe a change and the AI guesses the region. Inpainting lets you paint exactly where the edit should happen. Use the editor for broad changes ("make it sunset"); use inpainting for precise local edits.
Retouch is the premium-only, Kontext-only, small-defect-fixing flavor — ideal for blemish removal and skin work. Inpainting exposes the same mask UX plus Standard and Seedream models with full prompt control, for any kind of local edit.
JPG, PNG, and WebP up to 10 MB. The mask is generated client-side at native resolution and sent as a PNG alongside the image.
On clean mask edges with realistic prompts, yes — Kontext Pro and Seedream blend to match surrounding lighting and texture. Jagged masks, misspelled prompts, or physically impossible requests will show seams.
No. Input image + mask are processed and discarded. The inpainted output is kept on our CDN for 24 hours (7 days for paid users) so you can re-download or share.
Yes. POST a multipart form with image + mask + prompt to /v1/image/edit/ with mode=inpaint (Standard) or mode=retouch (Kontext/Seedream). See /api/ for the full spec.
How would you rate this tool?