Image to PSD with layers: split any image into editable layers

Use an image to layers converter: upload the picture here and press Split into layers. The model separates each element onto a transparent layer and fills in the background behind them, then you download a layered PSD. On Seedream 5.0 Flash it costs 1 credit per output image; one run returns the background plus up to 16 layers.

No. JPEG and PNG store one flat image, which is why a plain JPG-to-PSD converter gives you a single layer. To get real layers the image has to be taken apart — that is what the AI split does.

Saving or renaming a PNG as .psd gives a PSD with one layer, because a PNG holds one flat image. A PNG to PSD with layers converter has to take the picture apart instead. Upload the PNG here: each element (people, products, text, logos) goes onto its own transparent layer, up to 16 per pass on Auto, the background behind them is filled in, and about one to two minutes later you download a PSD that opens in Photoshop, Photopea or Affinity. Social media graphics, banners and thumbnails work the same way. The first split is free with a Gmail sign-in.

For JPG to PSD with layers, upload the JPG on this page, leave the layer count on Auto (or pick 3, 4, 6 or 8) and press Split into layers. About one to two minutes later every element (people, products, text, logos) is on its own transparent layer with the background filled in behind it; download the PSD and open it in Photoshop, Photopea or Affinity. The first split is free with a Gmail sign-in (1K, background + 4 layers); after that each output image costs 1 credit on Flash. To see the result before uploading anything, open one of the samples: every layer can be toggled and exported.

No. A flat image does not remember how it was built. The layers are rebuilt by the model from what it sees, and areas that were covered are repainted, so fine details can differ from the original file.

You cannot undo the flattening itself: a flat JPG or PNG keeps only the final pixels, not which object each pixel belonged to, and whatever was covered is gone. What you can do is rebuild the layers. By hand in Photoshop that means Select Subject or the Object Selection tool, a layer mask and Generative Fill for every element in turn, typically 30–60 minutes for a 10-element design. Here it is one upload: every element goes onto its own transparent layer (up to 16 per pass on Auto), the covered areas behind them are repainted, text comes back as layers you can export as editable type, and you download the PSD about one to two minutes later. The repainted areas are new pixels, so check them before you reuse the file.

Look for the original first: Photoshop’s auto-recovery files, Creative Cloud version history, backups, old email attachments, or the designer who made it. The JPG itself does not contain the layers, so no tool can recover them from it. If the PSD is gone for good, rebuild it: upload the JPG here and press Split into layers. Each element and line of text comes back on its own transparent layer with the background filled in, and “PSD with editable text” turns the text it can read into Photoshop type. It is a rebuilt file, not your original: fonts are matched by style rather than by name, and covered areas are repainted.

Images from ChatGPT, Midjourney and Gemini download as one flat picture, so Photoshop opens them as a single layer. Download the image at full size (in Midjourney, upscale it first), upload it here and press Split into layers. About one to two minutes later the character, each object and each line of text are on their own transparent layers with the background filled in, and the PSD opens in Photoshop. If you can still regenerate, another route is to ask ChatGPT for each element separately on a transparent background and stack them yourself; splitting keeps the exact image you already chose.

If you stay in Canva, Canva Magic Layers separates an uploaded graphic into editable elements inside a Canva design, but Canva does not download PSD. If you need a layered file for Photoshop, Photopea or Affinity, upload the graphic here: posts, stories, banners and thumbnails come back with each photo, shape, logo and line of text on its own transparent layer and the background filled in. Export “PSD with editable text” to get the text as Photoshop type, or a ZIP of PNGs to rebuild the post in another editor. The first split is free with a Gmail sign-in.

Choose Auto to split as finely as possible (up to 16 elements per pass, with extra passes on busy images), or ask for 3, 4, 6 or 8 layers and the model merges the rest into them. Fewer layers cost less and finish sooner.

Sign in with a Gmail account for one free try (a 1K split into background + 4 layers, or one text edit). After that you pay with credits, billed per output image: 1 credit on Flash or 6.7 credits on Pro. Credits come in one-time packs; there is no subscription.

Yes. LayerPSD splits an image into layers online, in the browser, and the first split is free: sign in with a Gmail account for a 1K split into background + 4 layers, with PSD and ZIP export. After that each output image costs 1 credit on Flash. If it has to be free every time, Photopea is a free online editor that saves PSD files, but there you cut each layer out by hand.