agentleFS
meitumeitu/meitu-skills/skills/image-edit/SKILL.md

image-edit

Skill33 starsChanged 5 months agoMITView on GitHub

兼容已有 `image-edit` 名称和直接 CLI 调用的图片编辑 Skill。新的底图编辑、重绘、融合或衍生请求优先由 image-to-image 路由;用户明确指定 image-edit 时仍使用本 Skill。会读取 Meitu 凭证、调用本地 `meitu` CLI,并将输入图片与提示词发送到 Meitu OpenAPI,结果写入本地输出目录。

  • Reads credentials
  • Installs packages

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use flux-2-klein, flux-kontext and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • agentspace-soSkill

    flux-2-klein

    Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux 2 Klein's strengths (sub-second latency, multi-reference brand styling, declarative subject-first prompts), the step-count strategy (4–8 for fast iteration, ~25 for polish), the 9B vs 4B variant trade-off, and when to route to Flux 2 Pro / Seedream 5 / GPT Image 2 instead. Calls `runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image` (or `/4b/`) through the local RunComfy CLI. Triggers on "flux 2 klein", "flux-2-klein", "flux klein", "BFL flux 2", or any explicit ask to generate with this model.

    Also in 4 projects that use this

  • agentspace-soSkill

    flux-kontext

    Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

    Also in 4 projects that use this

  • prime-skillsSkill

    image-inpainting

    Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the target area. Triggers on "inpaint", "inpainting", "image inpaint", "remove from image", "fill region", "mask-driven edit", "remove watermark", "remove object", "patch the photo", "fill the hole", or any explicit ask to edit a specific masked region of a still.

    Also in 4 projects that use this

  • prime-skillsSkill

    ace-step

    Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step audio-inpaint (regenerate a time range inside an existing track), ACE Step audio-outpaint (extend an existing track before or after). Triggers on "ace step", "ace-step", "acestep", "ACE music", "open music model", "cheap AI music", "inpaint audio", "audio inpaint", "extend music", "audio outpaint", "lengthen track", "music with tags", or any explicit ask to generate or edit music with ACE Step.

    Also in 3 projects that use this

  • +3 more from agentspace-so
  • +5 more from prime-skills

The file

Files
SKILL.md

图生图(image-edit)

Overview

对已有图片施加内容编辑或基于参考图创作全新图片(必须有底图)。覆盖 5 类场景:电商产品出图(白底/场景/多角度/带文字)、人像编辑(人脸/妆容/发型/姿态)、多图与一致性编辑、通用编辑(替换/添加/构图)、参考图创作(创意视觉稿/名片/封面)。涉及文字添加/替换时目标文字内容保持原样不翻译;"IP"指角色图案而非文字。

执行前应让用户清楚知道:本 Skill 会读取本地 Meitu 凭证、调用 meitu image-edit,并把输入图片、提示词及生成结果发送到/写回外部服务与本地输出目录。

API Mapping

  • 人像编辑:image_gummy_edit_v45
  • 多图/一致性/通用/电商/参考图创作(主):image_praline_edit_v2
  • 通用编辑(降级):image_praline_edit_2
  • 工具内兜底:image_mint_edit
  • Nougat 高质量(外部显式指定):image_nougat_edit(路由不识别;image_list 最多 10 张;不支持 output_format;size 内部常量 2K;quality 由 API 内部默认 Medium 不对外暴露)

model 映射:auto(默认按路由)/gummy_pro→gummy/praline_pro→v2/praline_lite→2/mint_edit→mint/nougat→nougat_edit(外部显式指定触发)

Dependencies

  • meitu-cli: >=2.0.6(npm install -g meitu-cli@latest)
  • 凭证:CONFIG AKSK → meitu tools update;EXEC AKSK → 实际执行(见根 CONFIG.md)
  • 环境变量:MEITU_OPENAPI_TOOL_TASK_MODE=command

路径别名:$VISUAL = {OPENCLAW_HOME}/workspace/visual/

Core Workflow

Preflight → Execute → Deliver

Preflight

  1. meitu --version ≥ 2.0.6(否则 npm install -g meitu-cli@latest)
  2. 确认已跑过 meitu tools update(用 CONFIG AKSK)
  3. 当前 AKSK = EXEC,且 MEITU_OPENAPI_TOOL_TASK_MODE=command
  4. 解析 output_dir:openclaw.yaml → ./output/ |else → $VISUAL/output/image-edit/;mkdir -p

Execute

触发信号 / 路由规则

核心判断维度:电商产品出图 → 前置判断(参考图创作 / 多图)→ 单图场景分类。

决策顺序: 0. 前置 0 — 电商产品出图:产品图 + 电商意图(白底/主图/场景/多角度/促销文字) → image_praline_edit_v2

  1. 前置 A — 参考图创作:有参考图 + 生成全新图意图 → image_praline_edit_v2
  2. 前置 B — 多图输入:image_list ≥ 2 张 → image_praline_edit_v2(强制使用 image_list)
  3. 单图场景(优先级:人像 > 一致性 > 通用):
    • 人像(人脸/表情/妆容/发型/肤色/姿态/五官) → image_gummy_edit_v45
    • 一致性(商品微调/保持主体/已有图片文字替换) → image_praline_edit_v2
    • 通用(替换/添加/构图) → image_praline_edit_v2

参数定义

通用参数(所有 API 共用):

参数类型必填说明
image_listARRAY[STRING]是图片地址列表,所有 API 统一使用。缺失 → 提示"请提供图片"
promptSTRING是编辑描述。文字添加/替换场景目标文字保持用户原文不翻译;"IP"指图案/角色而非文字

image_praline_edit_v2 额外参数:

参数类型必填范围默认值说明
ratioSTRING否auto/1:1/2:3/3:2/3:4/4:3/4:5/5:4/9:16/16:9/21:9auto特殊比例需在 prompt 结尾写 Aspect ratio x:y
sizeSTRING否1K/2K/4K--输出分辨率
output_formatSTRING否jpeg/png/webpjpeg输出格式

model 参数(可显式指定绕过 auto 路由):gummy_pro(人像)/praline_pro(通用)/praline_lite(降级)/mint_edit(兜底)/nougat(高质量,外部显式指定触发,路由不识别)。

工具调用

meitu image-edit \
  --skill_name skill_image-edit \
  --image_list <url1,url2> \
  --prompt "<edit_description>" \
  --json \
  --download-dir {output_dir}

可选:--ratio 1:1 --size 2K --output_format png --model praline_pro

错误降级

场景处理方式
image_gummy_edit_v45 失败重试 1 次 → 降级 image_praline_edit_v2,后续按 v2→2→mint
image_praline_edit_v2 失败重试 1 次 → 降级 image_praline_edit_2(多图取 image_list[0])
image_praline_edit_2 失败重试 1 次 → 降级 image_mint_edit
image_mint_edit 失败返回错误
内容合规拦截返回合规提示,不重试、不降级
多图 + 人像意图强制走 v2(gummy 仅支持单图),建议拆分单张处理
prompt 含目标文字文字内容保持原样、不翻译
prompt 含"IP"保留"图案/角色"语义,不得转为"文字"

Deliver

  • 直接使用 Preflight 解析的 output_dir
  • 从 downloaded_files[0].saved_path 读取已下载文件路径
  • mv {downloaded_files[0].saved_path} {output_dir}/{YYYY-MM-DD}_{descriptive}_image-edit.{jpeg|png|webp}

Output

  • 格式:JPEG(默认)/PNG/WebP(由 output_format 决定)
  • 命名:{YYYY-MM-DD}_{descriptive}_image-edit.jpg
  • 位置:项目 → ./output/,一次性 → $VISUAL/output/image-edit/

基线 Task ID

见 references/task-id-baseline.md 中对应行。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.