AI image expander

Your photo goes in the middle of a canvas of the frame you pick, and an image model continues the scene into the empty space, matching perspective, light, colors and style. The middle stays your original, pixel for pixel, so it is exactly as it was.

No. The expander keeps the original picture exactly as it is, uncropped, and adds only the new area around it. The middle of the result is your own photo's pixels, blended at the seam; only the space around it is new. The result is the original plus more scene.

Yes. Uncropping, extending and outpainting are names for the same job: the expander keeps your photo as it is and adds new scene around it in the frame you pick. The new area is the model's continuation of the scene, not what was really there.

16:9, 9:16, 1:1, 4:3, 3:4, 4:5 and 21:9. All but 3:4 and 4:5 are frames DreamBench's video models render, so expanding to the frame your clip will use gives the video model a reference that already fits. 4:5 is the tallest an Instagram feed post can be.

Only what lies beyond the edge of your photo: more of the same room, sky or street, not what was really there. A busy scene expanded by a lot can repeat its patterns or soften toward the far edge, and a face at the old edge is the hardest thing to continue: expand in smaller steps, keep the subject off the border, and check the seam at full size.

Yes, AI can extend the background of a photo, and backgrounds are what it does best. Pick the frame you need and the sky, wall, floor or street is continued past the old edge in the same light and perspective, while your photo's own pixels stay untouched in the middle. People and objects cut off at the edge are finished by guesswork, so keep them away from the border.

Yes. Choose 9:16 vertical. A landscape or square photo grows upward and downward so the subject keeps its place in the frame. Keep faces and text clear of the top and bottom, where the apps put their buttons, and the result can start a 9:16 clip in the composer.

To expand an image without stretching it, add new scene around it instead of resizing it. Stretching pulls pixels out of shape, so faces and circles look wrong; expanding keeps the photo in its own proportions in the middle and draws more of the scene past its edges until it fills the new frame. This page never stretches: make it with any DreamBench plan.

Expanding a photo does not change your photo's own pixels: the middle of the result is the original, and the new border is drawn to match its light and grain. A large upload is scaled down first so the wider canvas fits, so the result can have fewer pixels than your upload; for a big print, run it through the AI image upscaler afterward.

No. You pick one of seven frames and the photo sits in the middle of it, so the new scene is added on the sides the frame needs, equally. There is no custom canvas or one-sided expand here, and the result is a JPEG with no transparency.

No. There is no prompt on this page: the scene is continued as it is, more of the same sky, room or street. To change what is in the picture, edit it with the AI photo editor before or after you expand it.

Yes, in either phone's browser, with no app to install. Choose the photo from your camera roll, an iPhone's HEIC photo included, which is converted on the phone before the run. Pick the frame, press Expand the image, and download the result full size. Each run takes one photo, so expand several one by one with the same frame.

No. DreamBench adds no watermark to the image you download; the result is a JPEG of your photo and the new border around it. The image model that drew the border may embed an invisible mark of its own.

No. Expanding a photo needs a DreamBench plan, and you create an account on the way to it. The button shows each run's price in credits before you press it, and a run that fails is refunded.

No. It expands one still photo; a video's frame can't be extended here. An expanded photo can start a new clip, though: press Animate this frame and the composer opens with it as the reference, set to the clip frame nearest the one you picked.

Yes: Canva's Magic Expand and Photoshop's Generative Expand both add scene around a photo, inside their own editors and plans, and on an iPhone with Apple Intelligence, Extend in the Photos app does it from iOS 27. This tool takes one photo and a frame, keeps your own pixels in the middle, and opens the result in the composer as a reference for a clip.

A run starts at 8 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 110 runs of the AI image expander, 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.