qwen-edit by digitalsamba/claude-code-video-toolkit
npx skills add https://github.com/digitalsamba/claude-code-video-toolkit --skill qwen-edit通过 RunPod 无服务器服务,使用 Qwen-Image-Edit-2511 进行 AI 驱动的图像编辑。
状态: 演进中 - 实验过程中正在总结学习经验
当用户想要:
# 基本编辑
python tools/image_edit.py --input photo.jpg --prompt "Add sunglasses"
# 使用负面提示词(推荐)
python tools/image_edit.py --input photo.jpg \
--prompt "Reframe as portrait with full head visible" \
--negative "blur, distortion, artifacts"
# 风格迁移
python tools/image_edit.py --input photo.jpg --style cyberpunk
# 背景(谨慎使用 - 经常失败)
python tools/image_edit.py --input photo.jpg --background office
# 更高质量
python tools/image_edit.py --input photo.jpg --prompt "..." --steps 16 --guidance 3.0
# 多图像合成(保持身份特征)
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
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
prompting.md - 提示词模式和结构examples.md - 实验中的好/坏示例parameters.md - 调整步数、引导系数、负面提示词tools/image_edit.py - RunPod 端点的 CLI 封装工具
docs/qwen-edit-patterns.md - 角色转换模式.ai_dev/qwen-edit-research.md - 研究笔记每周安装量
54
代码仓库
GitHub 星标数
108
首次出现
2026年1月28日
安全审计
安装于
opencode45
codex44
cursor44
gemini-cli42
claude-code41
github-copilot41
AI-powered image editing using Qwen-Image-Edit-2511 via RunPod serverless.
Status: Evolving - learnings being captured as we experiment
Use when the user wants to:
# Basic edit
python tools/image_edit.py --input photo.jpg --prompt "Add sunglasses"
# With negative prompt (recommended)
python tools/image_edit.py --input photo.jpg \
--prompt "Reframe as portrait with full head visible" \
--negative "blur, distortion, artifacts"
# Style transfer
python tools/image_edit.py --input photo.jpg --style cyberpunk
# Background (use cautiously - often fails)
python tools/image_edit.py --input photo.jpg --background office
# Higher quality
python tools/image_edit.py --input photo.jpg --prompt "..." --steps 16 --guidance 3.0
# Multi-image composite (identity-preserving)
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
prompting.md - Prompt patterns and structureexamples.md - Good/bad examples from experimentsparameters.md - Tuning steps, guidance, negative promptstools/image_edit.py - CLI wrapper for RunPod endpoint
docs/qwen-edit-patterns.md - Character transformation patterns.ai_dev/qwen-edit-research.md - Research notesWeekly Installs
54
Repository
GitHub Stars
108
First Seen
Jan 28, 2026
Security Audits
Gen Agent Trust HubWarnSocketPassSnykPass
Installed on
opencode45
codex44
cursor44
gemini-cli42
claude-code41
github-copilot41
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
50,900 周安装