Qwen-Image-Edit Skill

Qwen-Image-Edit 技能

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

Status: Evolving - learnings being captured as we experiment

通过RunPod无服务器架构，基于Qwen-Image-Edit-2511实现的AI驱动图像编辑工具。

状态： 持续演进中——我们会在实验过程中不断总结经验

When to Use This Skill

适用场景

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.)

当用户需要以下操作时可使用本技能：

编辑/转换照片时保留人物身份
重构裁剪后的图像（修复被截断的头部等问题）
更换服装、添加配饰
调整姿势（手臂位置、手部摆放）
应用风格迁移（赛博朋克、动漫、油画风格）
调整光线/色彩分级
添加/移除物体
角色转换（邦德、尼奥等）

When NOT to Use

不适用场景

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

单张图片背景替换——会产生抠图伪影、光晕效果
人脸互换——无法从参考图中保留身份特征
图像外扩——无法可靠地扩展画布

Use With Care

谨慎使用场景

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)

多图像合成——搭配明确的身份锚点可实现（详见examples.md中的提示词模式）。需要描述人物的独特特征（发质/发色、种族、服装），并将guidance参数设置为约2.0
相机角度变更——结果不稳定。垂直角度（低角度/高角度）比旋转角度（四分之三视角）效果更好

Quick Reference

快速参考

bash

undefined

bash

undefined

Basic edit

基础编辑

python tools/image_edit.py --input photo.jpg --prompt "Add sunglasses"

With negative prompt (recommended)

使用反向提示词（推荐）

python tools/image_edit.py --input photo.jpg
--prompt "Reframe as portrait with full head visible"
--negative "blur, distortion, artifacts"

Style transfer

风格迁移

python tools/image_edit.py --input photo.jpg --style cyberpunk

Background (use cautiously - often fails)

背景替换（谨慎使用——通常效果不佳）

python tools/image_edit.py --input photo.jpg --background office

Higher quality

更高质量输出

python tools/image_edit.py --input photo.jpg --prompt "..." --steps 16 --guidance 3.0

Multi-image composite (identity-preserving)

多图像合成（保留身份）

python 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

undefined