playbooks

home / skills / openclaw / skills / image-edit

image-edit skill

/skills/ivangdavila/image-edit

This skill helps you edit images with AI inpainting, outpainting, background removal, upscaling, and restoration to enhance visuals with precision.

npx playbooks add skill openclaw/skills --skill image-edit

Review the files below or copy the command above to add this skill to your agents.

Files (9)
SKILL.md
2.7 KB
---
name: Image Editing
description: Edit images with AI inpainting, outpainting, background removal, upscaling, and restoration tools.
metadata: {"clawdbot":{"emoji":"✂️","os":["linux","darwin","win32"]}}
---

# AI Image Editing

Help users edit and enhance images with AI tools.

**Rules:**
- Ask what edit they need: remove objects, extend canvas, upscale, fix faces, change background
- Check technique files: `inpainting.md`, `outpainting.md`, `background-removal.md`, `upscaling.md`, `restoration.md`, `style-transfer.md`
- Check `tools.md` for provider-specific setup
- Always preserve original file before editing

---

## Edit Type Selection

| Task | Technique | Best Tools |
|------|-----------|------------|
| Remove objects/people | Inpainting | DALL-E, SD Inpaint, IOPaint |
| Extend image borders | Outpainting | DALL-E, SD Outpaint, Photoshop AI |
| Remove background | Segmentation | remove.bg, ClipDrop, Photoroom |
| Increase resolution | Upscaling | Real-ESRGAN, Topaz, Magnific |
| Fix blurry faces | Restoration | GFPGAN, CodeFormer |
| Change style | Style Transfer | SD img2img, ControlNet |
| Relight scene | Relighting | ClipDrop, IC-Light |

---

## Workflow Principles

- **Non-destructive editing** — keep originals, save edits as new files
- **Work in layers** — combine multiple edits sequentially
- **Match resolution** — edit at original resolution, upscale last
- **Mask precision matters** — better masks = better results
- **Iterate on masks** — refine edges for seamless blends

---

## Masking Basics

Masks define edit regions:
- **White** = edit this area
- **Black** = preserve this area
- **Gray** = partial blend (feathering)

**Mask creation methods:**
- Manual brush in editor
- SAM (Segment Anything) for auto-selection
- Color/luminance keying
- Edge detection

---

## Common Workflows

### Object Removal
1. Create mask over unwanted object
2. Run inpainting with context prompt (optional)
3. Blend edges if needed
4. Touch up artifacts

### Background Replacement
1. Remove background (get transparent PNG)
2. Place on new background
3. Match lighting/color
4. Add shadows for realism

### Enhancement Pipeline
1. Restore faces (if present)
2. Remove artifacts/noise
3. Color correct
4. Upscale to final resolution

---

## Quality Tips

- **Feather masks** — hard edges look artificial
- **Context prompts help** — describe what should fill the area
- **Multiple passes** — large edits may need iterative refinement
- **Check edges** — zoom in to verify blend quality
- **Match grain/noise** — add film grain to match original

---

### Current Setup
<!-- Tool: status -->

### Projects
<!-- What they're editing -->

### Preferences
<!-- Preferred tools, quality settings -->

---
*Check technique files for detailed workflows.*

Overview

This skill provides AI-powered image editing tools for inpainting, outpainting, background removal, upscaling, and restoration. It guides you through non-destructive, layer-based workflows to preserve originals while producing high-quality edits. The skill supports iterative mask refinement, provider-specific tool selection, and final quality checks for seamless results.

How this skill works

You describe the desired edit (remove object, extend canvas, change background, upscale, or restore), supply the image and an edit mask or selection, and the skill runs the appropriate AI technique. It chooses inpainting for object removal, outpainting for extension, segmentation for background removal, specialized upscalers for resolution boosts, and restoration models for faces and noise reduction. Outputs are saved as new files, and recommended post-processing (blending, color matching, grain) is applied to integrate edits naturally.

When to use it

  • Remove distractions or unwanted people from photos
  • Extend an image to change composition or add context
  • Replace or remove backgrounds for product or portrait shots
  • Improve resolution for prints or detailed crops
  • Restore old, blurry, or damaged photos for archiving

Best practices

  • Always keep the original file; perform edits on copies to stay non-destructive
  • Create precise masks and feather edges to avoid hard seams
  • Work at the image’s native resolution; upscale only after finishing edits
  • Iterate: run multiple passes for large fills or complex restorations
  • Match lighting, color, and grain when compositing new backgrounds or fills

Example use cases

  • Remove a lamp post from a landscape photo using inpainting and a context prompt
  • Outpaint a smartphone photo to create room for titles or web banners
  • Remove background from product shots, then place products on a neutral or styled backplate
  • Restore a scanned family photo: denoise, repair faces, and upscale for print
  • Enhance a portrait by fixing blurry eyes, color-correcting skin tones, and adding subtle grain for realism

FAQ

Do edits overwrite the original image?

No. The workflow always preserves the original and writes edits to new files to keep the process non-destructive.

How do I get clean fills for large removed areas?

Use precise masks, provide a context prompt describing surrounding content, and perform iterative inpainting passes with edge blending to refine results.