JuneYaooo/gpt-image2-ppt-skills
gpt-image2-ppt
VerifiedGenerate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection>/STYLE_ID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx. Use when the user asks to make a presentation, slides, deck, pitch deck, investor PPT, magazine-style PPT, or 做一份 PPT / 生成幻灯片 / 用 gpt-image 生成 PPT / 按这个模板生成 PPT.
examples/editable-pptx/case05-summer-poster/README.md
View on GitHub# Case 05:夏日星星人可编辑海报
这个案例展示如何保留 `gpt-image-2` 完整视觉稿的美感,同时把文字、基础图形和复杂主视觉重建为可分别操作的 PowerPoint 对象。
**[下载可编辑 PPTX](./editable.pptx)**
## 原始视觉与可编辑结果
<table>
<tr>
<th width="50%">原始完整视觉稿</th>
<th width="50%">可编辑 PPTX 的 Office 回渲染</th>
</tr>
<tr>
<td><img src="./original.png" width="100%" alt="Case 05 原始完整视觉稿"></td>
<td><img src="./rendered.png" width="100%" alt="Case 05 可编辑 PPTX 回渲染"></td>
</tr>
</table>
重建后的版式、色彩、材质和主视觉关系与原稿保持一致,但 PPTX 中实际包含 **13 个可选对象**。
## 拆成了哪些对象
| 对象类型 | 数量 | 内容 | 在 PowerPoint 中可以做什么 |
| --- | ---: | --- | --- |
| 原生文本 | 5 | 顶部标语、主标题、限定徽章文字、产品名、底部说明 | 修改文字、字体、字号、颜色和位置 |
| 原生 shape | 6 | 水彩文字面板、夏日徽章、产品横幅、3 颗装饰星 | 修改填充、描边、大小和位置 |
| Clean plate | 1 | 水彩天空、云朵、荷叶、荷花和整体光感 | 作为完整背景保持画面质感 |
| 独立图片层 | 1 | 星星人、粽子冰淇淋及其重叠关系 | 整组移动、缩放、旋转或替换 |
## Clean plate:移走对象后不会露出重影
文字面板、文案和右侧主视觉已经从背景中移除。用户移动文字或主视觉时,底下不会再出现一份模型原先画出的重复对象。

## 独立主视觉素材
星星人、粽子冰淇淋与顶部星星存在明显遮挡关系。默认策略不是把每个被遮挡对象强行拆成残缺碎片,而是把它们作为一个完整组合层提取,保留原来的构图和叙事关系。
<p align="center">
<img src="./layers/mascot-icecream-group.png" width="48%" alt="透明底星星人与粽子冰淇淋组合素材">
</p>
## 透明边缘检查
毛绒、白色冰淇淋、半透明高光和水彩边缘很容易出现白边、黑边或残留底色,因此透明素材同时放到白底和黑底上检查。
<table>
<tr>
<th width="50%">白底检查</th>
<th width="50%">黑底检查</th>
</tr>
<tr>
<td><img src="./edge-check-white.png" width="100%" alt="透明素材白底边缘检查"></td>
<td><img src="./edge-check-black.png" width="100%" alt="透明素材黑底边缘检查"></td>
</tr>
</table>
## 为什么这个案例使用 B 路线
可编辑模式对重叠素材采用 A1 → A2 → B 路由:
1. **A1 原像素直接提取(默认)**:原素材轮廓完整、边缘干净时,直接从完整视觉稿中提取;互相重叠的素材默认保留为一个组合层。
2. **A2 原像素 + 遮挡补全**:保留能看到的原像素,只补全被遮挡区域以及对象移走后暴露的背景。
3. **B AI 分离或重生成**:只有 A1/A2 的边缘或补全效果不合格,或者用户明确要求设计模式时才升级。
本页同时包含黄色毛绒、白色冰淇淋、水彩云、细小高光和多层遮挡。A1/A2 的直接抠图测试在毛发与浅色边缘处不稳定,因此升级到 B:参考原图生成单色键背景的完整组合素材,再进行本地去背景和黑白底复核。
## 哪些内容仍然保留为图片
可编辑不等于把每个像素都转成 PowerPoint 矢量图形。水彩背景继续作为 clean plate,毛绒角色和食物摄影质感继续作为透明图片层;这些内容如果硬转成 shape,反而会明显损失 `gpt-image-2` 的美感。
文字、规则面板、徽章、横幅和装饰星则适合用 PowerPoint 原生对象重建,因此可以直接编辑。这种混合方式兼顾视觉质量和实际修改能力。
## 验证材料
- [下载可编辑 PPTX](./editable.pptx)
- [查看页面对象清单(scene)](./slide-01.scene.json)
- [查看质量报告](./quality-report.json)
质量报告记录了 1 页、5 个原生文本、6 个原生 shape、1 个独立图片层和 2 个图片对象(clean plate + 独立主视觉)。最终 PPTX 已通过真实 Office 渲染和人工视觉检查。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |