SceneFlare

Seedream 5.5 Layerize

Split one JPEG or PNG into a base image and transparent PNG layers. Download placement and stacking data, with optional text recognition.

Source files

0/1
Seedream 5.5 Layerize preview

Recover separate elements from a flattened design

Use Seedream 5.5 Layerize on SceneFlare when you have a finished graphic and need to move or reuse individual elements. The model estimates the layers from the visible image, so inspect overlapping areas before using the pieces in a new layout.

Plan your split

Start with one clear image

Upload one PNG or JPEG, up to 30 MB, with at least 262,144 total pixels. Keep the elements you want to separate large enough to see.

Set an output limit

Choose 2–100 outputs, including the base image. Leave the prompt blank for automatic detection or name the few elements you need, such as the heading and the main illustration.

Use the placement data to rebuild

Download the transparent PNG layers and their JSON file. The file lists stacking order and bounding boxes so you can position the layers relative to the base image.

SceneFlare example

Coffee poster, separated into six layers

We left the prompt blank. Layerize returned a base image and separate PNGs for the headline, subtitle, pink shape, saucer, cup and coffee beans. The artwork on the left is the input. The tiles show all six returned layers.

Read the headline in the metadata

Text recognition returned SUNDAY COFFEE and TASTING SESSION with their positions. The text layers are PNGs. Use the recognized words to set editable type again in your design tool.

Use the cup and saucer separately

Move the cup and saucer as separate pieces. The pink shape stops where the cup and saucer covered it, so check that edge if you move the ceramics.

Coffee poster, separated into six layers

Coffee poster and the returned base

Drag the divider to compare the finished poster with the base image Layerize returned.

Coffee poster and the returned base returned base
Coffee poster and the returned base coffee poster
Coffee posterReturned base

Skincare ad, separated into four layers

We asked for the bottle, leaf, limestone platform and text. Layerize returned those four PNG layers and a base image. The headline and subtitle came back together in one layer.

Check where the leaf meets the bottle

The leaf layer ends at the area covered by the bottle. Moving the bottle can expose that edge, so preview the pieces together before changing the layout.

Compare the two runs

Both runs used 1K, a maximum of 10 outputs and text recognition. The poster used 24 SceneFlare credits and the ad used 18, after unused credits were returned.

Skincare ad, separated into four layers

Skincare ad and the returned base

The base still shows the droplet and part of the platform. Inspect what remains on the base before rebuilding the ad.

Skincare ad and the returned base returned base
Skincare ad and the returned base skincare ad
Skincare adReturned base

Split a poster into layers

01

Upload the flattened artwork

Choose a single JPEG or PNG. For a first run, use a design with a clear background and distinct shapes.

02

Set the split and review the quote

Pick an output limit and turn on Text recognition if the design has a heading or label you want to recover. Sign in and check the maximum charge.

03

Download and align the pieces

Download the layers and layer metadata. Place the PNGs using the bounding boxes and stacking order, then check any areas that were covered by other objects.

Layerize questions

Will this restore my original Photoshop layers?

You receive a base image, transparent PNGs and JSON. Any previously hidden pixels are estimated, and the result contains neither the original layer history nor editable type.

What text can it recognize?

Enable Text recognition for regular printed text. Handwriting and decorative lettering may not return OCR data. Check the recognized words before reusing them.

How are credits settled?

SceneFlare reserves for the maximum number of outputs. The final charge includes the input, the base image and each returned layer at its size tier. Unused credits are returned.