art → rig-ready

Material separation for Live2D, with AI doing the boring half

Cubism wants your character cut into parts on named PSD layers. The coarse cuts (hair masses, face, body, clothing) are exactly what AI separation is good at. Do those in minutes here, spend your hands on the parts that deserve them.

Start separating a character

What Cubism actually needs

Live2D's own docs describe the target: hair split into bangs/sides/back, face parts separated (eyes broken into lashes, whites, irises; mouth split for open/closed), body and limbs on their own layers, each as filled raster layers in one PSD. Traditionally that is hours in Photoshop or Clip Studio per character. None of it is creatively interesting work. It is segmentation, which is now a solved problem for the coarse 80%.

The AI-assisted workflow

Load the character art. Use AI grab to click out the big masses — hair front, hair back, face, torso, each arm, clothing pieces — lifting each to a named layer; flat-shaded art also responds extremely well to Split by color, which put this test character's hair, skin, hoodie, and pants on separate layers in one click. Rename layers to Cubism's conventions as you go, and export a PSD whose groups arrive intact in the Cubism editor.

Character art split into part layers in the editor — A flat-shaded character after one Split by color — parts on named layers, real output.

What still needs your hands (honesty section)

AI will not correctly split eyelashes from eye whites, or build the closed-mouth interior Cubism wants: the sub-part surgery and the paint-behind work (extending hair BEHIND the face so it can swing) remain manual, here with the brush tools or in your paint app. What you save is the hours of outlining every large region. Riggers we'd be lying to: this is a first-pass accelerator, not a rig generator.

Also works for Spine, Moho, and cutout animation

The same coarse-parts-on-layers preparation feeds any 2D rigging tool — Spine, Moho, After Effects puppet workflows. Export PSD for tools that read it, or the PNG stack for engines that want individual part images.

Frequently asked

Will the PSD open correctly in Cubism?

Cubism requires raster layers with fill, which is what we write. Combine line art and fill per part (Cubism's own requirement), keep layer names clean, and the import is standard.

Can it split eyes and mouth automatically?

Not to Cubism's sub-part granularity — lashes, whites, and mouth interiors need manual work. The AI handles the large-mass separation that eats most of the clock.

Does it handle painted (non-flat) art?

Yes — AI grab works on painted shading. Split by color is the shortcut specifically for flat-shaded/cel styles.

Your product photos, as layered files you own Split a background into parallax planes for your 2D game How PSD layer writing actually works Remove the object, fill the background, and keep the object Canva can't make layers from an image. Here's the workaround.Get image layers into PowerPoint: the clean way Make a depth-effect wallpaper from your own image Separate the subject from the background, and keep both Pull the text out of an image — as text you can actually edit Most "image to PSD" converters are fake. Here is the 30-second test.Color separation for screen printing, without the $500 software Turn a flat image into a PSD with real layers Split any image into separate, editable layers Split an image into layers — by object, or by color An AI layer separator that hands you a real file Turn any image into a layered .ora for GIMP and Krita One photo in. The layered file you actually need, out.