Remove Text from Image
Brush over a date stamp, caption, subtitle, watermark phrase, or any writing burned into a photo, and the AI rebuilds the surface underneath. Free, no signup, 5 removes a day.
Before / After
Erase unwanted objects and clutter
Before & after
In short
To remove text from an image free: upload the photo, paint over the words with the brush, and tap Remove text. In about 20 seconds the AI repaints the masked region to match the surrounding surface, so the writing disappears. It works on date stamps, subtitles, captions, watermark text, meme headlines, signs, and handwriting — 3 images a day free, 5 after a Google sign-in, no watermark on the result. Note: it erases text, it does not read or translate it.
Where burned-in text comes from
Text gets baked into an image in dozens of ways. Older cameras and phones stamp an orange date and time into the corner of every shot. Streaming rips and short-form videos ship with hardcoded subtitles that cannot be toggled off. Stock agencies print “SAMPLE” or a diagonal copyright line across previews. Memes carry bold headline captions, and social apps add usernames and overlay labels when you share. Scanned documents arrive with handwriting, signatures, and price tags you may want gone.
Once text is rasterised into the pixels, there is no “hide layer” button — the letters are part of the picture, sitting on top of whatever was behind them. Removing them cleanly means rebuilding that hidden surface, which is exactly what AI inpainting does: it studies the pixels surrounding your brush and predicts a seamless continuation of the wall, sky, skin, or paper the words were covering.
For your own photos and content this is routine cleanup. For text that carries ownership or attribution — a photographer’s watermark, a copyright notice, an agency credit on a licensed image — check your rights first. Removing copyright management information can be a separate violation under US law (17 USC §1202) and equivalent rules elsewhere, independent of any underlying copyright.
How to remove text in 3 steps
- 1
Upload the image with text on it
Drag any JPG or PNG into the upload card or tap to browse — a holiday photo with an orange date stamp, a film still with hardcoded subtitles, a stock preview with diagonal text, a meme with bold captions, a scanned form with handwriting. Files wider than 1536 pixels are downscaled automatically before processing, so you never have to resize first. Aspect ratio is preserved end to end.
- 2
Brush over every word you want gone
Paint a mask across the text. For a single-line date stamp or caption a 20–35 pixel brush is plenty; for a large meme headline or a diagonal watermark phrase, widen the brush and paint the whole line in one continuous stroke. Add 3–5 pixels of margin past the letterforms — the descenders on g, y, p and the dots over i and j are easy to miss, and a stray pixel of ink leaves a visible smudge. The red overlay shows exactly which pixels get rewritten.
- 3
Download the clean image
Tap Remove text. In roughly 20 seconds the AI reads the area around your mask — the wall, sky, skin, paper, or gradient behind the letters — and repaints the masked region to match, so the writing disappears into a continuous surface. Hit Download to save a PNG at your upload's dimensions. The text is gone; the surface it sat on is rebuilt.
Text types this removes
A quick reference for the most common cases, the brush size that works, and how cleanly each tends to rebuild.
| Text type | Typical example | Brush size | Difficulty |
|---|---|---|---|
| Date & time stamps | "08 15 2009" burned in orange by an old camera | 20–35 px | Easy |
| Subtitles & captions | Hardcoded subtitles on a film or TikTok still | 25–45 px line | Easy |
| Watermark text | "SAMPLE", agency name, diagonal © phrase | 40–90 px line | Medium |
| Meme & overlay text | Bold white Impact headline, 'POV' labels | 50–100 px | Easy |
| Signs & labels in the scene | A shop sign, a name tag, a license plate string | 30–70 px | Hard |
| Handwriting & document text | A note on a form, a signature, a price tag | 20–50 px | Medium |
Tips for cleaner results
Catch the descenders and accents
Letters like g, j, p, q, y drop below the baseline, and i, j, é, ñ carry marks above. A tight mask that hugs the main body of the text often leaves these stragglers behind as faint specks. Paint a few pixels past the obvious edges.
Paint a whole line, not letter by letter
Continuous text rebuilds more cleanly in one pass. Brushing each word separately leaves the AI guessing at the gaps between them, which can show as faint seams where two predictions meet.
Uniform surfaces vanish best
Text over sky, a painted wall, paper, skin, or a smooth gradient is reconstructed almost perfectly. Text sitting on busy texture — foliage, brick, patterned fabric, or another piece of text — is harder, and may leave soft residue you can touch up afterwards.
Outlined or shadowed text needs a wider mask
Caption text often has a dark stroke or drop shadow for legibility. Paint past the stroke, not just the coloured fill, or a thin outline ghost of the letters can remain.
What it can and can’t do
It removes text — it does not read or translate it
This is an eraser, not OCR. The AI never decodes the words; it just rebuilds the surface they covered. If you need the text extracted or translated, use an OCR tool first, then clean the image here.
Whatever was behind the text is reconstructed, not recovered
When a caption covers part of a face or a detailed object, the AI invents a plausible continuation from the surrounding pixels. On a plain wall that is invisible; over fine detail it is an educated guess, not the true hidden content.
Tiny low-contrast text can need a steady hand
A pale timestamp on a bright sky is easy to miss. Zoom your browser in (Cmd/Ctrl +) and paint its known location even if you can barely see it — the AI cleans faint regions just as well once they are masked.
Questions about removing text from images
Other specialised removers
Remove Watermark from Photo
Tuned for diagonal © lines, stock 'SAMPLE' banners, and dense watermark text across a whole frame.
Remove Sticker from Image
Erase emoji, chat bubbles, and overlay graphics from screenshots and social exports.
Remove Date Stamp from Photo
Sub-variant for the burned-in orange date stamps on old camera and camcorder photos.