Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

A practical guide to AI videos with Doubao digital human avatars

AI summary

A Juejin tutorial organizes eight video scenarios for Doubao digital human avatars, including product presentations, daily-life stories, multi-character dialogue, historical costumes, workplace scenes, science fiction, concerts and anime interactions. The author describes the avatars as speaking photographs that support expressions, speech, head turns and small hand gestures, but are less suitable for large walking motions or loud crying. It also provides prompt-writing and workflow advice, such as alternating dialogue turns and using camera movement, scene changes and sound effects to compensate for limited body motion.

In-depth insight

The guide offers concrete, source-supported prompts and workflows for creators experimenting with AI-generated presenters and fictional characters in Doubao.

前言

上篇文章 笔者介绍了如何用豆包创建真人分身并生成视频。文章发出后,粉丝群里收到了一条回复:

“我的分身做好了,但是我可以拿它来干什么呢?”

笔者盯着这句话看了半天。当前大模型能力越来越强,创作门槛越来越低,真正拉开作品差距的,往往不是工具,而是创作者的创意。

本篇文章笔者整理了8个可以利用真人分身创作的AI视频场景,希望能启发大家:让分身替我们出镜,去演那些我们现实中根本拍不了的角色。建议先收藏,今晚挑一个场景试一条。

一、先搞清楚:真人分身能演什么,不能演什么?

1.1 真人分身的能力边界:它不是演员

这里先说一个笔者踩过的坑:分身不是演员。

#Doubao

Original · 9 min readRead the original
Group chat

No comments yet. Start the conversation.