AI object remover

To remove an object from a photo, upload the photo, type what should go and where it is, such as the red trash can on the left, and press Remove it. The model erases the object and fills the gap with what would be behind it, keeping the rest of the picture close to the original. Make the edit with any DreamBench plan and download it full size.

No. The object remover works from your description. Saying where it is helps: the person on the left, the sign above the door, the cup nearest the camera. If two things fit the words, name the one you mean by its place or its color, or both may go.

An AI object remover fills the background by inpainting: it paints new pixels into the space the object covered, continuing the wall, grass or sky around it with the same light and perspective. The fill is a plausible continuation, not the real view the object was hiding, so check busy scenes at full size.

Yes, for pictures you own or have the right to edit. Name the text and its position, such as the white caption in the bottom right corner. A logo on your own product photo comes off the same way; a brand's logo or a watermark on someone else's work is not what it is for, and removing a watermark doesn't change who owns the image.

The gap is painted from what surrounds it, and a busy pattern, a crowd or strong shadows are hard to continue cleanly, so the fill can look soft or patchy. Run it again with a narrower description of the object and where it sits; each run is a fresh attempt.

On a plain wall, sky, floor or lawn, the background usually looks natural after removing an object: the surface carries on through the gap. Behind a large object in a detailed scene the model has more to invent, so the fill can look soft. Run it again with a narrower description if it does.

Yes, with a brush: Canva's Magic Eraser, Google Photos' Magic Eraser, Samsung's Object Eraser and Clean Up in Photos on iPhones with Apple Intelligence erase what you paint over. This tool works from a sentence instead, which suits things that are hard to paint, such as long wires, and it runs in the browser on a phone, tablet or computer, Android or iPhone, Mac or Windows.

They work differently. Photoshop's Remove tool and Generative Fill, and Lightroom's Remove, fill an area you paint, so only that area changes. This tool works from a sentence and redraws the picture with the object gone, which suits things that are hard to paint, such as a tangle of wires. For a pixel-exact edit elsewhere in the picture, use a brush tool.

No. Removing the background cuts the subject out and leaves it on transparent or white, which the AI background remover does. This tool keeps the whole scene and takes one thing out of it, filling the gap. Use both when a product photo needs a stray cable gone and a white background.

Not here: this page only removes. The AI image editor takes an instruction in your own words for the change you want in the clean scene, such as what should stand where the trash can was. Remove first and edit second if the gap should be clean before anything new goes in; each run is priced separately.

It can. The picture is drawn again at the image model's own size, so a large upload can come back with fewer pixels than it had, in the same proportions. For a large print, enlarge the clean photo with the image upscaler, which adds pixels without redrawing anything.

No. It edits one still photo at a time. Remove what you need from a still here, then press Animate the clean photo to open the composer with it as a reference, where DreamBench's video models make a new clip.

It is instructed not to: the same framing, colors and details everywhere outside the removal. The picture is drawn again by an image model, though, so small text and fine detail elsewhere can drift slightly. Compare the before and after in the page before you download.

No. Every run needs a DreamBench plan; you create an account on the way, and the button shows the price in credits before you press it. The tools come with every plan, alongside the video models, and a run that fails is refunded.

No. The tool takes one photo per run, and there is no batch upload. Run it again for the next one, with its own description: each run is priced separately, and the button shows the price before you press it.

No visible one. A DreamBench tool adds no watermark to an image it returns, on any plan. The image model that fills the gap embeds SynthID, Google's invisible mark that identifies a picture as made or edited by AI; it changes nothing you can see, and the download is the clean photo full size.

A run starts at 7 credits from your DreamBench plan, depending on the photo, and once you have a plan the button shows each run's price before you press it. Starter, $9.99 a month, includes 1,100 credits a month, at least 122 runs of the AI object remover, plus AI video. A run that fails is refunded.

Yes: a free account and a DreamBench plan. The tools are part of every plan, from Starter at $9.99 a month.

A photo up to 40 megabytes: JPEG, PNG, WebP, HEIC or another format your browser opens. A photo straight from a phone is fine, an iPhone's HEIC included: the page scales a large picture down to 2048 pixels on its long edge before the run, so the result is never larger than the page says.

Yes. Under the DreamBench Terms you may use what a tool makes for personal and commercial purposes, including advertising, monetized content and work for clients, with no separate commercial-use upgrade. The Terms don't guarantee copyright in a result or clear another person's rights in your upload, so only use photos you have the rights to.

No. DreamBench doesn't use your prompts, uploads or videos to train or fine-tune AI models, and any future training program would be opt-in.

It stays in your browser until you make a result. Then it is used to make that result and nothing else, and removed from the tool's storage after seven days along with the result. A result you keep in your library stays as long as you keep it.