← Back to Skills Marketplace
metahuan

Yufluentcn Ecommerce Imaging

by metahuan · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
26
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install yufluentcn-ecommerce-imaging
Description
跨境电商 AI 生图:白底图、场景图、实拍抠图、多角度套装、多平台尺寸。 经 Yufluent 云端 Replicate 代理(Qwen-Image 等),按张计费。 配合 visual-craft 工作流 brief→生图→合规。 Use for 生成产品白底图、场景图、AI 电商图片、产品摄影、主图.
README (SKILL.md)

电商 AI 生图

跨境 白底图 / 场景图 / 实拍抠图 / 多角度套装 生成。ClawHub / OpenClaw 云端模式 — 生图在 Yufluent 服务端通过 Replicate 代理执行,按张计费;本机只需 TOKENAPI_KEYtk-*)与 requests

支持上传实拍图 URL 或本地路径做 img2img(多角度套装必填)。

OpenClaw 与 Yufluent(必读)

OpenClaw 对话与技能调用共用同一 tk-*。接入见 https://claw.changzhiai.com/app/openclaw

走哪里 干什么
OpenClaw 对话 Yufluent /v1/chat/completions(同一 tk-*) 选场景/角度/尺寸、调 run.py
生图正式输出 POST /v1/skills/ecommerce-imaging/run(同一 tk-*) 服务端 Replicate → 图片 URL

Agent 硬性规则:

  1. 禁止用对话模型自行生成图片或给出图片生成指令替代本技能。
  2. 必须通过 python scripts/run.py ...(或 POST /v1/skills/ecommerce-imaging/run)获取输出。
  3. 对话模型仅用于:确认场景、尺寸、角度、上传实拍图路径、解释结果。
  4. 只需 TOKENAPI_KEY不要要求用户另配厂商 LLM Key 或 Replicate Token。

Instructions(Agent 工作流)

  1. 确认场景(见下表);默认 white_bg。客户有实拍图 → --source-image
  2. 收集参数
    • --product(必填)
    • --scene:白底/厨房/客厅/多角度套装/节日场景等
    • --platform-size:如 amazon-mainamazon-aplus-banner
    • --source-image:实拍图 URL 或本地路径
    • --brand-style:品牌调性叠加(luxury_minimal / youthful_pop 等)
  3. 调用(必须 — 云端)
    python scripts/run.py \
      --product "不锈钢不粘锅" \
      --scene white_bg \
      --platform-size amazon-main
    
  4. 多角度套装
    python scripts/run.py \
      --product "蓝牙耳机" \
      --scene multi_angle_pack \
      --source-image "./front.jpg"
    
  5. 计费:按张计费;402 余额不足;401 密钥无效。

场景列表

场景 key 说明
white_bg 纯白背景产品图
minimal_white 极简白底
modern_kitchen 现代厨房
living_room 客厅场景
lifestyle 生活场景
desk_setup 桌面场景
multi_angle_pack 多角度套装(需 --source-image
节日/促销 christmas, prime_day, black_friday, valentine, summer_sale

环境变量

变量 必填 说明
TOKENAPI_KEY tk-*Yufluent 控制台 获取
TOKENAPI_BASE_URL 默认 http://localhost:8080/v1

触发词

  • "生成产品白底图"
  • "做场景图"
  • "AI 生成电商图片"
  • "产品主图"
  • "多角度展示"
  • "product image"

Examples

白底图

python scripts/run.py \
  --product "不锈钢不粘锅" \
  --scene white_bg \
  --platform-size amazon-main

厨房场景图

python scripts/run.py \
  --product "陶瓷餐具套装" \
  --scene modern_kitchen \
  --brand-style eco_natural

实拍图抠图换背景

python scripts/run.py \
  --product "蓝牙耳机" \
  --scene white_bg \
  --source-image "./product.jpg"

多角度套装

python scripts/run.py \
  --product "蓝牙耳机" \
  --scene multi_angle_pack \
  --source-image "./front.jpg"

工作流联动

visual-to-imaging:visual-craft (main_image brief) → ecommerce-imaging 生图 → visual-craft (image_compliance) 合规检查。

合规声明

  • AI 生成图片需人工审核产品质量一致性后再上架
  • 不生成侵权商品图、违禁品或虚假宣传图片
  • 平台主图规则(如 Amazon 纯白底不低于 85%)以平台最新要求为准

版本记录

版本 日期 变更
v1.0.0 2026-06-13 规范 SKILL.md:补充 Agent 规则、Instructions、触发词、示例、环境变量、合规、版本记录
v0.1.0 初始电商 AI 生图技能
Usage Guidance
Install only if you are comfortable sending product descriptions and any source product images to the configured Yufluent/OpenClaw API for paid cloud generation. Keep TOKENAPI_KEY private, set TOKENAPI_BASE_URL only to a trusted service, and avoid uploading confidential or regulated product images unless that data handling is acceptable.
Capability Tags
requires-sensitive-credentials
Capability Assessment
Purpose & Capability
The stated purpose is paid ecommerce image generation through Yufluent/Replicate, and the artifacts consistently implement that by collecting product/image parameters and calling a cloud API.
Instruction Scope
The trigger phrases are fairly broad and the instructions tell the agent to use the cloud workflow, so users should expect billable remote calls when invoking ecommerce image-generation requests.
Install Mechanism
Installation metadata requests only the TOKENAPI_KEY environment variable and a pip dependency on requests; no privileged install hooks or unrelated packages were found.
Credentials
Network access, API credentials, prompt payloads, and optional source-image upload are proportionate to the cloud image-generation purpose, though TOKENAPI_BASE_URL is user-configurable and should be kept trusted.
Persistence & Privilege
No background service, startup persistence, privilege escalation, or destructive behavior was found; direct Replicate helper code may write generated images and a local log, which fits the tool purpose.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install yufluentcn-ecommerce-imaging
  3. After installation, invoke the skill by name or use /yufluentcn-ecommerce-imaging
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
yufluentcn-ecommerce-imaging 1.0.0 - Initial public release for AI-powered ecommerce image generation. - Supports white background, scene images, cutout from real photos, multi-angle packs, and various platform sizes. - Cloud-based execution via Yufluent's Replicate proxy, pay-per-image. - Integrates with visual-craft workflow for automated compliance checks. - Provides detailed agent instructions, environment variable setup, trigger words, and usage examples in SKILL.md. - Includes compliance guidelines and versioning history.
Metadata
Slug yufluentcn-ecommerce-imaging
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Yufluentcn Ecommerce Imaging?

跨境电商 AI 生图:白底图、场景图、实拍抠图、多角度套装、多平台尺寸。 经 Yufluent 云端 Replicate 代理(Qwen-Image 等),按张计费。 配合 visual-craft 工作流 brief→生图→合规。 Use for 生成产品白底图、场景图、AI 电商图片、产品摄影、主图. It is an AI Agent Skill for Claude Code / OpenClaw, with 26 downloads so far.

How do I install Yufluentcn Ecommerce Imaging?

Run "/install yufluentcn-ecommerce-imaging" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Yufluentcn Ecommerce Imaging free?

Yes, Yufluentcn Ecommerce Imaging is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Yufluentcn Ecommerce Imaging support?

Yufluentcn Ecommerce Imaging is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Yufluentcn Ecommerce Imaging?

It is built and maintained by metahuan (@metahuan); the current version is v1.0.0.

💬 Comments