LogoThread Easy
  • Explorar
  • Componer hilo
LogoThread Easy

Tu compañero integral para hilos de Twitter

© 2025 Thread Easy All Rights Reserved.

Explorar

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

SCAIL-Preview
代码:
https://t.co/dBWzCds3wh
https://t.co/T8r7b6gie5

模型:
https://t.co/43f1xKGPGF
https://t.co/CINx8aMXSn

RealVideo
代码:https://t.co/3qlZ08UQkE
模型:
https://t.co/6k86GIg7q0
https://t.co/dlnEFGdBj6

Kaleido
代码:https://t.co/NqSB9JlguW

模型:
https://t.co/0rpcHg1YzD
https://t.co/lAFNHJ8yDk

SSVAE
代码:https://t.co/J9e2EsbNRz

模型:

SCAIL-Preview 代码: https://t.co/dBWzCds3wh https://t.co/T8r7b6gie5 模型: https://t.co/43f1xKGPGF https://t.co/CINx8aMXSn RealVideo 代码:https://t.co/3qlZ08UQkE 模型: https://t.co/6k86GIg7q0 https://t.co/dlnEFGdBj6 Kaleido 代码:https://t.co/NqSB9JlguW 模型: https://t.co/0rpcHg1YzD https://t.co/lAFNHJ8yDk SSVAE 代码:https://t.co/J9e2EsbNRz 模型:

致力于让每个想拥抱AI的人都能找到适合自己的AI产品,助力企业定制AIGC应用

avatar for AIGCLINK
AIGCLINK
Fri Dec 12 11:07:56
发一下今天智谱刚刚开源的视频四件套:SCAIL、RealVideo、Kaleido、SSVAE,姿势、实时流式、多主体都有了

其中的RealVideo,实时流式视频生成,首响延迟2-3秒,3秒语音克隆,可上传头像,能输出数分钟的连续对话或演讲视频,实现2秒虚拟主播开播

SCAIL,给一张演员照片+3D骨骼动作,就能生成空翻、街舞等复杂多人交互镜头,肢体不崩、遮挡不乱

还有一个多主体视频生成框架Kaleido、频谱结构化变分自编码器VAE SSVAE

#AI视频 #AI直播 #GLM

发一下今天智谱刚刚开源的视频四件套:SCAIL、RealVideo、Kaleido、SSVAE,姿势、实时流式、多主体都有了 其中的RealVideo,实时流式视频生成,首响延迟2-3秒,3秒语音克隆,可上传头像,能输出数分钟的连续对话或演讲视频,实现2秒虚拟主播开播 SCAIL,给一张演员照片+3D骨骼动作,就能生成空翻、街舞等复杂多人交互镜头,肢体不崩、遮挡不乱 还有一个多主体视频生成框架Kaleido、频谱结构化变分自编码器VAE SSVAE #AI视频 #AI直播 #GLM

SCAIL-Preview 代码: https://t.co/dBWzCds3wh https://t.co/T8r7b6gie5 模型: https://t.co/43f1xKGPGF https://t.co/CINx8aMXSn RealVideo 代码:https://t.co/3qlZ08UQkE 模型: https://t.co/6k86GIg7q0 https://t.co/dlnEFGdBj6 Kaleido 代码:https://t.co/NqSB9JlguW 模型: https://t.co/0rpcHg1YzD https://t.co/lAFNHJ8yDk SSVAE 代码:https://t.co/J9e2EsbNRz 模型:

avatar for AIGCLINK
AIGCLINK
Fri Dec 12 11:07:55
RT @bingyikang: Need to run DA3 on super-long videos or small GPUs?

We are releasing DA3-Streaming (code) — a memory-efficient inference p…

RT @bingyikang: Need to run DA3 on super-long videos or small GPUs? We are releasing DA3-Streaming (code) — a memory-efficient inference p…

Founder and CEO of https://t.co/5MjtfpwEU3 | Your guide to radiance fields | Host of the podcast @ViewDependent | FTP: 279 | discord: https://t.co/lrl64WGvlD

avatar for MrNeRF
MrNeRF
Fri Dec 12 11:01:22
This Week in Laravel: API-First Projects, AI-Generated CRUDs, and More https://t.co/XKRx95AIN9

My tradition of a newsletter, as a public article.

This Week in Laravel: API-First Projects, AI-Generated CRUDs, and More https://t.co/XKRx95AIN9 My tradition of a newsletter, as a public article.

~20 yrs in web-dev, now mostly Laravel. My Laravel courses: https://t.co/HRUAJdMRZL My Youtube channel: https://t.co/qPQAkaov2F

avatar for Povilas Korop | Laravel Courses Creator & Youtuber
Povilas Korop | Laravel Courses Creator & Youtuber
Fri Dec 12 10:45:03
Orthographic Projection, perhaps useful for cleanups? Anyway, it looks cute.

Orthographic Projection, perhaps useful for cleanups? Anyway, it looks cute.

Founder and CEO of https://t.co/5MjtfpwEU3 | Your guide to radiance fields | Host of the podcast @ViewDependent | FTP: 279 | discord: https://t.co/lrl64WGvlD

avatar for MrNeRF
MrNeRF
Fri Dec 12 10:44:01
RT @getpy: DSPyWeekly Issue 15 - 12th Dec 2025 is out 

This week is absolutely stacked with:

🎙️ Omar Khattab chats with Martin Casado (a1…

RT @getpy: DSPyWeekly Issue 15 - 12th Dec 2025 is out This week is absolutely stacked with: 🎙️ Omar Khattab chats with Martin Casado (a1…

Asst professor @MIT EECS & CSAIL (@nlp_mit). Author of https://t.co/VgyLxl0oa1 and https://t.co/ZZaSzaRaZ7 (@DSPyOSS). Prev: CS PhD @StanfordNLP. Research @Databricks.

avatar for Omar Khattab
Omar Khattab
Fri Dec 12 10:33:50
  • Previous
  • 1
  • More pages
  • 914
  • 915
  • 916
  • More pages
  • 5634
  • Next