A practical wrapper around Qwen-Image-Edit-2511 for identity-preserving photo edits. Works well for reframing cropped portraits, changing clothing and poses, and style transfers like cyberpunk or anime. The documentation is refreshingly honest about limitations: background replacement creates halos, face swapping doesn't work, and outpainting is unreliable. Multi-image compositing can work but needs explicit identity anchors in your prompts describing ethnicity, hair texture, and outfit details. The skill captures real experimental learnings with concrete prompt patterns and parameter tuning guidance. If you need to fix a headshot that cut off the top of someone's head or transform a photo while keeping the person recognizable, this is worth trying.
- skills.sh installs
- 1.2K
- GitHub stars
- 2.5K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add digitalsamba/claude-code-video-toolkit --skill qwen-edit --agent claude-codeInstalls into .claude/skills of the current project.
Files
Qwen-Image-Edit Skill
AI-powered image editing via tools/image_edit.py. The model depends on the deployment:
| Deployment | Model | License | Defaults | Max inputs |
|---|---|---|---|---|
--cloud modal (default) | Qwen-Image-Edit-2511 | Apache-2.0, commercial OK | 8 steps, guidance 1.0 | 3 images |
--cloud modal, app deployed with IMAGE_EDIT_MODEL=qwen-image-2.1 | Qwen-Image-2.1 (2026-09, unified gen+edit, 7B DiT, RGBA) | Qwen Research License -- non-commercial ("research or evaluation purposes only") | 40 steps, guidance 1.0 (no CFG) | 10 images |
--cloud runpod | Qwen-Image-Edit-2511 + Lightning LoRA | Apache-2.0, commercial OK | 8 steps, guidance 1.0 | 3 images |
The tool prints Model: and Steps: after each edit, so you can tell which model the Modal app
runs and how many steps it took. Without --steps, each model runs its own default above.
Opt in with IMAGE_EDIT_MODEL=qwen-image-2.1 uv run modal deploy docker/modal-image-edit/app.py;
deploy again without it to switch back.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/digitalsamba/claude-code-video-toolkit
- Categories
- Code Review & Quality, AI & Agent Building, Generative Media
- First seen
- Jun 3, 2026
More from digitalsamba/claude-code-video-toolkit
All 12Recommended
More Code Review & Quality
vtex-io-security-boundariesvtex/skillsApply when reviewing or designing security-sensitive boundaries in VTEX IO apps. Covers public versus private exposure, trust assumptions at route and integrati1.2Kskills.sh installs
video-downloaderdavila7/claude-code-templatesDownloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.1.2Kskills.sh installs
localization-strategykostja94/marketing-skillsWhen the user wants to plan or implement localization strategy for multilingual and global growth. Also use when the user mentions "localization," "multilingual1.2Kskills.sh installs
github-automationruvnet/rufloGitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR 1.2Kskills.sh installs
react-composition-2026patternsdev/skillsTeaches modern React composition patterns for 2025/2026. Use when designing component APIs, building shared UI libraries, or refactoring prop-heavy components.1.2Kskills.sh installs
framer-motionpproenca/dot-skillsFramer Motion performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring React animations with Framer Motion to ensu1.2Kskills.sh installs