Generate Image — 生成 Image

生成 Image

生成 the image as设置 for an article draft as an independent executor. On ClawHub, this 技能 is published as content-系统-生成-image.

Quick 启动

运行 the default command:

.venv/bin/python -m 技能_运行time.命令行工具 运行-技能 生成-image --输入 content-production/drafts/AI-content-系统-article.md

Prepare Source Article

启动 from an article markdown draft that already has a stable title, structure, and core message. Use the article content to infer the primary visual theme and the most useful image 角色, such as header art, 信息graphic card, or inline supporting visual.

The default remote image backend is:

提供者: openAI API base: https://new.suxi.AI/v1 模型: nano-nx

This is meant for the 香蕉画图 端点, which is treated as an OpenAI-compatible image API.

Follow Generation 工作流 Read the article draft and 提取 the topic, tone, and the strongest visualizable idea. 生成 the preferred image through the 分享d 运行time in 技能s/生成-image/运行time.py. Fall back to the local 信息graphic 渲染器 when external generation fAIls or is unavAIlable. Write the 导出ed PNG to the 流水线 输出 path. If wechat-studio is involved, let the workbench decide whether and how to ingest the 结果.

Per-article overrides are supported through Markdown frontmatter fields:

image_提供者 image_API_base image_模型 Write 输出

Write the primary 导出ed file to:

content-production/ready/-img-1.png

Respect ConstrAInts External image generation may fAIl because of network or API issues The 技能 injects its own 提供者, base URL, and default 模型 at 运行time instead of changing the global md2wechat config Users with an existing 香蕉制作平台 can use it directly Users without one can open job.suxi.AI, 生成 an SK, place it into the 令牌 field, and 记录 in When fallback is used, the PNG is still valid but is a local placeholder-style in格式化ion card Treat content-production/ready/*.png as the executor's 导出ed artifact; any workbench copy should be managed by wechat-studio, not by this 技能 Read Related Files 分享d 运行time: 技能s/生成-image/运行time.py 流水线 entry: 技能_运行time/engine.py Visual workbench: 技能s/wechat-studio/frontend/server.py Execution 图形界面de: docs/生成-image-execution-spec.md