AI image editing prompting patterns for Qwen-Image-Edit

Qwen-Image-Edit Skill

by digitalsamba · MIT license · ★ 2,114 on GitHub · updated Sep 21

AI image editing prompting patterns for Qwen-Image-Edit. Use when editing photos while preserving identity, reframing cropped images, changing clothing or accessories, adjusting poses, applying style transfers, or character transformations.

---
name: qwen-edit
description: AI image editing prompting patterns for Qwen-Image-Edit. Use when editing photos while preserving identity, reframing cropped images, changing clothing or accessories, adjusting poses, applying style transfers, or character transformations. Provides prompt patterns, parameter tuning, and examples.
---

# Qwen-Image-Edit Skill

AI-powered image editing using Qwen-Image-Edit-2511 via RunPod serverless.

**Status:** Evolving - learnings being captured as we experiment

## When to Use This Skill

Use when the user wants to:
- Edit/transform photos while preserving identity
- Reframe cropped images (fix cut-off heads, etc.)
- Change clothing, add accessories
- Change pose (arm positions, hand placement)

Overview

AI-powered image editing using Qwen-Image-Edit-2511 via RunPod serverless.

Manual install (npx, ZIP)

Claude Codenpx skills add digitalsamba/claude-code-video-toolkit --skill qwen-edit -g -a claude-code

Claude Code (manual)

mkdir -p ~/.claude/skills && curl -sL https://codeload.github.com/digitalsamba/claude-code-video-toolkit/tar.gz/225c80a1c3a5 \
  | tar -xz -C ~/.claude/skills --strip-components=3 claude-code-video-toolkit-225c80a1c3a5/.claude/skills/qwen-edit

Windows (PowerShell)

New-Item -ItemType Directory -Force "$HOME\.claude\skills" | Out-Null; Invoke-WebRequest "https://m.agentalley.io/zip/756e42b663660714e330/qwen-edit.zip" -OutFile "$env:TEMP\qwen-edit.zip"; Expand-Archive "$env:TEMP\qwen-edit.zip" -DestinationPath "$HOME\.claude\skills" -Force

Claude.ai / desktopDownload the ZIP and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md2.8 KB
examples.md6.6 KB
parameters.md2.8 KB
prompting.md2.9 KB

Read the files here

digitalsamba/225c80a4 files

Shared references2SKILL.md reads these from elsewhere in the repo. Not in the ZIP.

Get them on GitHub ↗

SKILL.md

Show the full text76 lines

qwen-edit/SKILL.md76 lines · 2.8 KB

PreviewCode

Outline

RawView on GitHub

Qwen-Image-Edit Skill

AI-powered image editing using Qwen-Image-Edit-2511 via RunPod serverless.

Status: Evolving - learnings being captured as we experiment

When to Use This Skill

Use when the user wants to:

Edit/transform photos while preserving identity
Reframe cropped images (fix cut-off heads, etc.)
Change clothing, add accessories
Change pose (arm positions, hand placement)
Apply style transfers (cyberpunk, anime, oil painting)
Adjust lighting/color grading
Add/remove objects
Character transformations (Bond, Neo, etc.)

When NOT to Use

Background replacement (single image) - creates cut-out artifacts, halos
Face swapping - cannot preserve identity from reference
Outpainting - can't extend canvas reliably

Use With Care

Multi-image compositing - CAN work with explicit identity anchors (see examples.md for prompt patterns). Requires describing distinctive features (hair texture/color, ethnicity, outfit) and using guidance ~2.0
Camera angle changes - Inconsistent results. Vertical angles (low/high) work better than rotational (three-quarter view)

Quick Reference

# Basic edit
uv run tools/image_edit.py --input photo.jpg --prompt "Add sunglasses"

# With negative prompt (recommended)
uv run tools/image_edit.py --input photo.jpg \
  --prompt "Reframe as portrait with full head visible" \
  --negative "blur, distortion, artifacts"

# Style transfer
uv run tools/image_edit.py --input photo.jpg --style cyberpunk

# Background (use cautiously - often fails)
uv run tools/image_edit.py --input photo.jpg --background office

# Higher quality
uv run tools/image_edit.py --input photo.jpg --prompt "..." --steps 16 --guidance 3.0

# Multi-image composite (identity-preserving)
uv run tools/image_edit.py --input person.jpg background.jpg \
  --prompt "The [ethnicity] [gender] with [hair description] from first image is now in [scene] from second image. Same [features], [outfit]." \
  --negative "different ethnicity, different hair color, different face shape, generic stock photo" \
  --steps 16 --guidance 2.0

Key Files

prompting.md - Prompt patterns and structure
examples.md - Good/bad examples from experiments
parameters.md - Tuning steps, guidance, negative prompts

Tool Location

tools/image_edit.py - CLI wrapper for RunPod endpoint

docs/qwen-edit-patterns.md - Character transformation patterns
.ai_dev/qwen-edit-research.md - Research notes

1	---
2	name: qwen-edit
3	description: AI image editing prompting patterns for Qwen-Image-Edit. Use when editing photos while preserving identity, reframing cropped images, changing clothing or accessories, adjusting poses, applying style transfers, or character transformations. Provides prompt patterns, parameter tuning, and examples.
4	---
5
6	# Qwen-Image-Edit Skill
7
8	AI-powered image editing using Qwen-Image-Edit-2511 via RunPod serverless.
9
10	Status: Evolving - learnings being captured as we experiment
11
12	## When to Use This Skill
13
14	Use when the user wants to:
15	- Edit/transform photos while preserving identity
16	- Reframe cropped images (fix cut-off heads, etc.)
17	- Change clothing, add accessories
18	- Change pose (arm positions, hand placement)
19	- Apply style transfers (cyberpunk, anime, oil painting)
20	- Adjust lighting/color grading
21	- Add/remove objects
22	- Character transformations (Bond, Neo, etc.)
23
24	## When NOT to Use
25
26	- Background replacement (single image) - creates cut-out artifacts, halos
27	- Face swapping - cannot preserve identity from reference
28	- Outpainting - can't extend canvas reliably
29
30	## Use With Care
31
32	- Multi-image compositing - CAN work with explicit identity anchors (see examples.md for prompt patterns). Requires describing distinctive features (hair texture/color, ethnicity, outfit) and using guidance ~2.0
33	- Camera angle changes - Inconsistent results. Vertical angles (low/high) work better than rotational (three-quarter view)
34
35	## Quick Reference
36
37	```bash
38	# Basic edit
39	uv run tools/image_edit.py --input photo.jpg --prompt "Add sunglasses"
40
41	# With negative prompt (recommended)
42	uv run tools/image_edit.py --input photo.jpg \
43	--prompt "Reframe as portrait with full head visible" \
44	--negative "blur, distortion, artifacts"
45
46	# Style transfer
47	uv run tools/image_edit.py --input photo.jpg --style cyberpunk
48
49	# Background (use cautiously - often fails)
50	uv run tools/image_edit.py --input photo.jpg --background office
51
52	# Higher quality
53	uv run tools/image_edit.py --input photo.jpg --prompt "..." --steps 16 --guidance 3.0
54
55	# Multi-image composite (identity-preserving)
56	uv run tools/image_edit.py --input person.jpg background.jpg \
57	--prompt "The [ethnicity] [gender] with [hair description] from first image is now in [scene] from second image. Same [features], [outfit]." \
58	--negative "different ethnicity, different hair color, different face shape, generic stock photo" \
59	--steps 16 --guidance 2.0
60	```
61
62	## Key Files
63
64	- `prompting.md` - Prompt patterns and structure
65	- `examples.md` - Good/bad examples from experiments
66	- `parameters.md` - Tuning steps, guidance, negative prompts
67
68	## Tool Location
69
70	`tools/image_edit.py` - CLI wrapper for RunPod endpoint
71
72	## Related Docs
73
74	- `docs/qwen-edit-patterns.md` - Character transformation patterns
75	- `.ai_dev/qwen-edit-research.md` - Research notes
76