skills.rest
servitola
servitolaCOMMUNITY
Explore all skills by this author →
GitHub

image-edit

Automate image editing with cutout, inpaint, and generate pipelines.

12|2|Updated Feb 2, 2020
Search Tags:#text-to-image#inpainting#background-removal#photorealistic#image-edit#compositing#multiref
One-click install
npx skills add https://github.com/servitola/dotfiles --skill image-edit-servitola
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-edit
Source: https://github.com/servitola/dotfiles/tree/main/claude-code/skills/image-edit
Command: npx skills add https://github.com/servitola/dotfiles --skill image-edit-servitola

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gradio-client, Pillow, rembg, fal-client, google-genai, mlx, mflux, and includes references (resource) components.

What problem does it solve?

This skill consolidates multiple image-edit backends into a single workflow, enabling background removal, background replacement, region inpainting, and text-to-image generation for photos.

Core Features & Use Cases

  • Cutout: remove backgrounds to produce transparent PNGs suitable for compositing.
  • Edit: relight, place on new backgrounds, and compose multiple references into a single scene.
  • Inpaint: repaint a specified region using bbox or mask with support for iterative refinements and texture-fill fallbacks.
  • Generate: create fresh imagery from prompts when no input photo is used.
  • Use case: prepare product photos, enhance portraits, or generate variations from a base image.

Quick Start

Upload a photo and specify the edit you want (e.g., remove the background, relight, or place the subject on a new background).

Frequently Asked Questions about image-edit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove the background from a photo to create a transparent PNG?▼

Remove backgrounds from photos to produce transparent PNGs suitable for compositing using the cutout pipeline. This process isolates your subject automatically, providing a clean cutout for further editing or placement on new backgrounds.

Can I repaint a specific region of an image without changing the whole picture?▼

Repaint a specified region of an image using inpainting with bbox or mask inputs. This targeted tweak supports iterative refinements and texture-fill fallbacks, allowing you to modify specific areas while preserving the rest of the photo.

What is the best way to compose multiple reference images into a single scene?▼

Compose multiple reference images into a single scene by using the edit pipeline with optional references. This workflow allows you to relight subjects and place them on new backgrounds, merging different photos into one cohesive image.

Do I need an input photo to generate new photorealistic imagery?▼

You do not need an input photo to generate fresh imagery from prompts. The generate pipeline creates new photorealistic images from text-to-image prompts when no input photo is used, supporting use cases like product photo variations.

Does this image editing workflow support different backends for inpainting and compositing?▼

This image editing workflow supports multiple backends including edit_hfspace, edit_fal, edit_mflux, edit_gemini, and edit_pollinations. It leverages these alongside cutout_rembg to provide flexible relighting, compositing, and region inpainting capabilities.

Related Skills

Explore More Design & Creative Skills→
intellectronicaintellectronica
281

gpt-image-1-5

Generate and edit images with GPT Image 1.5 via scripts/generate_image.py.

Community
Intermediate
OrionUEOrionUE
16

splash-image-conversion

Convert source images into cropped Unreal Engine splash PNG and BMP assets.

Official
Intermediate
guia-matthieuguia-matthieu
145

image-batch

Automate batch image resizing, compression, background removal, watermarking, and format conversion with Python.

Community
Intermediate
1thirteeng31thirteeng3

stable-diffusion-image-generation

Generate photorealistic images from text prompts using Stable Diffusion via Diffusers.

Community
Advanced