Communitygithub.com

UGC 口播视频技能

把锁定人设静帧做成 9:16 UGC 口播视频:用 treg 跑 Seedance 2.5,自动控时长、配参考音色、烧字幕,一整套创作者流水线。

UGC 口播视频技能 是什么?

对接 Jason Zhou 公开的 AI UGC 工作流:先用 portrait-clone 锁脸,再用本技能定稿时长、抓音色参考、写 Seedance 2.5 提示词,经 treg(reAPI/PiAPI)出片,最后用 ffmpeg/PIL 烧 emoji 顶栏与短语字幕。专给要交片、不要空聊的 Agent。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/superdesigndev/treg/tree/main/.agents/skills/ugc-talking-head-video

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

UGC 口播视频技能 是做什么的?

Turn a locked character image (from portrait-clone) into a UGC-style 9:16 talking-head video: pick a voice-reference clip, size the script to the duration, write the Seedance 2.5 prompt, generate through treg (reAPI or PiAPI), then burn a static emoji header and phrase captions with code. Use after portrait-clone when the user wants the character to speak a script on camera.

Individual skills in this repo

This repo contains 1 individual skill — each has its own dedicated page.

相关技能