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

AIGCPanel v2.6.0 builds a digital human avatar from a single photo

AI summary

OSChina reports that AIGCPanel released v2.6.0, which lets users switch to an "image avatar" option in a dialog and upload a high-resolution front-facing selfie instead of recording a 10 to 30 second video with steady lighting and restrained expressions. The version also moves speech synthesis parameters to generation-time fine-tuning and adds fallback handling to task scheduling. The report says many users previously got stuck at the avatar-creation step, and it explicitly notes limits on the new capability.

In-depth insight

If the photo-based flow works as described, creating a digital human avatar shifts from recording a video to uploading one selfie, which is the central change in this release.

做数字人形象不用录视频了,一张自拍就行。语音合成参数改到生成时微调、任务调度补上兜底,也都在这一版里。📷 一张照片,就是一个数字人形象 过去建形象要录一段 10 到 30 秒的视频: 全程正脸、光线稳定、表情别太夸张。

不少人卡在第一步。现在弹窗里切到「图片形象」,传一张高清正脸自拍就能继续。先说清楚边界...

#AIGCPanel

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.