empty
3d3aba3670
feat: Add smart paragraph merging mode with AI grouping
...
Deploy Documentation / deploy (push) Has been cancelled
- Add "smart" split mode that uses LLM to intelligently merge related paragraphs
- Implement two-step approach: analyze text structure, then group by semantic relevance
- Add paragraph_merging.py with analysis and grouping prompts
- Update UI to support smart mode selection with auto-detect hint
- Add i18n translations for smart mode (en_US, zh_CN)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-17 00:19:46 +08:00
puke
3cf6628022
支持固定脚本多种分割方式(段落/行/句子)，修复Edge TTS和模板切换问题
2025-12-08 16:59:02 +08:00
张欣
1769b7faee
Update prompts and content generators
2025-12-05 16:42:17 +08:00
puke
ea784e0d06
支持基于图片素材的视频生成逻辑
2025-12-04 22:25:41 +08:00
puke
a9e12d539b
确保临时、数据和输出目录在返回路径之前存在
2025-11-21 11:22:11 +08:00
puke
c8df34a318
支持runninghub并行执行,提高视频生成效率
2025-11-17 14:33:51 +08:00
puke
9eb8e7f82d
Merge branch 'dev_video'
2025-11-12 21:22:08 +08:00
puke
4785d1ddb5
优化本地调用edge-tts的证书逻辑
2025-11-12 20:57:29 +08:00
puke
f7e3162a4a
webui适配视频功能; 统一模板命名规范;
2025-11-12 20:01:09 +08:00
puke
0e2b6b17d0
分镜支持视频功能
2025-11-11 20:38:31 +08:00
puke
abc611e4de
支持自定义PIXELLE_VIDEO_ROOT
2025-11-09 21:05:25 +08:00
puke
54d7271abc
添加代码版权声明
2025-11-07 16:59:47 +08:00
puke
9201bc0110
支持Docker容器化部署; 分离预设资源和自定义资源;
2025-11-07 16:59:12 +08:00
puke
22c46cf2c5
抽象pipeline逻辑
2025-11-07 16:59:12 +08:00
puke
77552c9e80
添加模板分组显示逻辑
2025-11-07 16:59:12 +08:00
puke
20e210b88d
显示具体的模板尺寸
2025-11-07 16:59:12 +08:00
puke
8333397615
更改视频尺寸的定义方式
2025-11-07 16:59:12 +08:00
puke
136514e466
项目重命名: ReelForge => Pixelle-Video
2025-11-07 16:59:12 +08:00
