[Feature] 朋友圈九宫格生成：一键智能选图+拼图+文案
Open
Nobody has claimed this yet.
enhancement
status: pending-review
- Dominant language
- Python
- Stars
- 739
- Forks
- 97
- Avg merge
- 10h 3m
- Merged PRs (30d)
- 82
Description
背景与目标
用户分享旅行照片到朋友圈时，需手动拼图、选图、配文。希望提供一键生成九宫格及配套文案，降低分享成本。
功能模块
智能选图
- 从旅行照片中 AI 选出 9 张最具代表性的照片
- 考虑：质量评分、内容多样性、时间分布
拼图样式
- 3×3 标准九宫格
- 自由排版（支持 1+2+6 等异形布局）
- 样式模板：简约、文艺、复古
文案生成
- 根据照片内容、景点生成文案
- 多种风格：诗意、幽默、简短
- 可选择添加话题标签
技术方案
- Canvas API 实现拼图
- 大模型生成文案（few-shot prompts）
- 支持预览和微调
优先级
高 - 强社交传播属性
相关文档
设计文档：/docs/dev/feature-proposals
This issue tracks the feature proposal for social media grid generation.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading /docs/dev/feature-proposals and reviewing how the project currently handles photo selection, previews, and generation; the proposal specifically calls for Canvas API composition and few-shot prompts. Done means a user can generate a nine-image grid, choose layouts and styles, preview and adjust it, and receive selectable travel copy with optional hashtags.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning, python
- Domain
- ai, computer-graphics, content, frontend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100