Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
All skills
Images

Remove the background

Cut the subject out of an image and deliver transparent, white, and brand-colour versions.

Use this skill in a chatOpens a new chat with it attached.

What it asks you for

Imagerequired
The image to cut out.
Deliver as
Which versions to produce.
Brand colour
Hex, when a brand version is wanted.

What it tells the AI to do

The full instructions, exactly as they run.

Cut the subject out of {{ image }}.

Deliver: {{ outputs | default("transparent") }}
Brand colour (when a brand version is wanted): {{ brandColor }}

Use a MATTING tool on an ephemeral computer (`rembg`, or ImageMagick when the
subject is cleanly separable) — do NOT re-generate the image with a diffusion
model. Re-generation changes the subject, which is the one thing a cutout must
preserve.

Steps:
1. `computer create` (or reuse one), upload the source to `/tmp/input/`.
2. Matte to a transparent PNG at `/tmp/output/`. Keep the original resolution.
3. Composite the extra requested backgrounds from the SAME matte, so every
   version has identical edges.
4. Check the alpha edge on hair/fur before delivering; a halo is the usual
   failure and is worth one refinement pass.
## Delivery

Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.
  • image
  • cutout
  • transparent

More images skills

  • Create an imageGenerate an image from a text prompt with a chosen model.
  • Edit an imageEdit an existing image using a natural-language instruction.
  • Upscale an image

Run it on your own work

idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.

Use Remove the background
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
Enlarge an image without re-generating it, preserving detail.
  • Resize for every formatTurn one master image into every aspect ratio you need, cropped so the subject survives.
  • Product shotPlace a real product into a new scene without altering the product itself.
  • Restyle an imageApply a visual style or reference look to an existing image.