正在加载视频...

视频加载失败

返回首页

Using SORA to generate and control an emotionally nuanced performance of a fully synthetic actor across several minutes of video. (Sound on)

KNGMKRlabs's profile picture

Matt Zien (KNGMKR)

2,609 subscribers

24,598 次观看 • 1 年前 •via X (Twitter)

教育科学技术艺术
LIVE

Anya Rossi• Live Now

Private livecam show

10 条评论

Elon's My Hero — e/acc 🤖FALSC 的头像
Elon's My Hero — e/acc 🤖FALSC1 年前

Who created the story and dialog?

Matt Zien (KNGMKR) 的头像
Matt Zien (KNGMKR)1 年前

I did! 😄

Baron de l’Agent 的头像
Baron de l’Agent1 年前

In addition really amazed by the lipsync. Feels so much better than what I have seen so far.

Shine by Nous ✨ 的头像
Shine by Nous ✨1 年前

Amazing job!! 🔥

Matt Zien (KNGMKR) 的头像
Matt Zien (KNGMKR)1 年前

Thank you Nous!

Guy Ben-Betzalel 的头像
Guy Ben-Betzalel1 年前

Amazing! Truly incredible!! What did you use for voice and lip syncing?

Jaycie | AI Creative Director 的头像
Jaycie | AI Creative Director1 年前

Dammmmmmmn. I'm floored.

Matt Zien (KNGMKR) 的头像
Matt Zien (KNGMKR)1 年前

thanks Jaycie!!!

wdrivex 的头像
wdrivex1 年前

Wow! With Act-One from Runway?

Matt Zien (KNGMKR) 的头像
Matt Zien (KNGMKR)1 年前

With @lipdubai

相关视频

here's how to create consistent characters with sora 2: sora just dropped character cameos and nobody's using it right the trick is you need to generate your character INSIDE sora first here's the exact process: - generate a video of your character standing/talking on white background in sora - hit the 3 dots -> create character - trim to the exact length you want - boom, now you have a reusable cameo normally you can't upload real people as cameos, but if you generate them in sora first, the system lets you save them this means you can now use the same AI character across 100+ videos without consistency issues video guide below
0:45

here's how to create consistent characters with sora 2: sora just dropped character cameos and nobody's using it right the trick is you need to generate your character INSIDE sora first here's the exact process: - generate a video of your character standing/talking on white background in sora - hit the 3 dots -> create character - trim to the exact length you want - boom, now you have a reusable cameo normally you can't upload real people as cameos, but if you generate them in sora first, the system lets you save them this means you can now use the same AI character across 100+ videos without consistency issues video guide below

Miko

16,019 次观看 • 10 个月前

I made a Sora MCP 🎬 The server can generate, remix, check video status, and even download videos to a folder of your choice Repo on GitHub 👇
0:33

I made a Sora MCP 🎬 The server can generate, remix, check video status, and even download videos to a folder of your choice Repo on GitHub 👇

Pietro Schirano

83,457 次观看 • 11 个月前

This is a powerful combination: 1) Directing an AI agent to generate characters, locations and all the angles I need for my dialogue shots 2) Using human actors to drive the performance of my characters The agent handles the technical side and I can focus on performance:
1:05

This is a powerful combination: 1) Directing an AI agent to generate characters, locations and all the angles I need for my dialogue shots 2) Using human actors to drive the performance of my characters The agent handles the technical side and I can focus on performance:

Halim Alrasihi

51,221 次观看 • 5 个月前

As you know, my explorations of the Gen AI space is ultimately all about creative control. You should be able to shape the generative matter using all your artistic sensibilities and your aesthetic sense. OpenAI's Sora is a huge technological leap, but what excites me the most about it is the modalities where it depends on input other than text alone. Such as video to video. Here's an example of how Sora can change an input video. Base video🧵
0:25

As you know, my explorations of the Gen AI space is ultimately all about creative control. You should be able to shape the generative matter using all your artistic sensibilities and your aesthetic sense. OpenAI's Sora is a huge technological leap, but what excites me the most about it is the modalities where it depends on input other than text alone. Such as video to video. Here's an example of how Sora can change an input video. Base video🧵

Martin Nebelong

7,520,483 次观看 • 2 年前

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.
2:05

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

The Humanoid Hub

20,968 次观看 • 1 年前

Video of Connor Storrie and Kathryn Hahn presenting the Actor Awards for Outstanding performance of a Female Actor in a Drama Series. #ConnorActorAwards
0:46

Video of Connor Storrie and Kathryn Hahn presenting the Actor Awards for Outstanding performance of a Female Actor in a Drama Series. #ConnorActorAwards

Connor Storrie Updates

116,001 次观看 • 6 个月前

I compiled 1 minute worth of footage across 7 videos. These are all prompts created using OpenAI's new Sora (text-to-video) model. Insane results.
1:00

I compiled 1 minute worth of footage across 7 videos. These are all prompts created using OpenAI's new Sora (text-to-video) model. Insane results.

Loopify 🧙‍♂️

126,829 次观看 • 2 年前

I just built and shipped my own personal Sora Video Studio using Replit ⠕ using the Sora API and launched to my own custom domain name. As the API evolves and improves I'll be able to have greater control of the videos made. It really feels like magic making software right now.
0:20

I just built and shipped my own personal Sora Video Studio using Replit ⠕ using the Sora API and launched to my own custom domain name. As the API evolves and improves I'll be able to have greater control of the videos made. It really feels like magic making software right now.

Levin Stanley

40,783 次观看 • 11 个月前

SORA 2 AND SORA 2 PRO ARE LIVE! The next-gen video model has landed on ImagineArt — bringing hyper-realistic visuals, natural physics, and cinematic SFX to life. 💎 1 Month FREE on Creator Plan 💰 Generate a Sora 2 video & Win $11,000 in the SORA 2 Challenge! #ImagineArt #Sora2
0:27

SORA 2 AND SORA 2 PRO ARE LIVE! The next-gen video model has landed on ImagineArt — bringing hyper-realistic visuals, natural physics, and cinematic SFX to life. 💎 1 Month FREE on Creator Plan 💰 Generate a Sora 2 video & Win $11,000 in the SORA 2 Challenge! #ImagineArt #Sora2

ImagineArt

512,966 次观看 • 11 个月前

OpenAI just dropped Sora 2 today it can generate videos with sound now, huge improvement on physics, realism, and control.. honestly no one can tell these are AI videos now here's everything you need to know:
0:25

OpenAI just dropped Sora 2 today it can generate videos with sound now, huge improvement on physics, realism, and control.. honestly no one can tell these are AI videos now here's everything you need to know:

el.cine

38,098 次观看 • 11 个月前

AI can now help you create beautiful animations. Here’s one of my recent tests. Workflow: - Generate images using Midjourney. - Use Sora or Flux Kontext to create additional camera angles. - Animate the images using Kling AI and/or Midjourney’s new video generator. - Generate music with Suno AI. - Put everything together using your favorite video editing tool. The potential is huge. This took less than an hour to complete from start to finish. Imagine what you could do with more time and a story to tell.
0:46

AI can now help you create beautiful animations. Here’s one of my recent tests. Workflow: - Generate images using Midjourney. - Use Sora or Flux Kontext to create additional camera angles. - Animate the images using Kling AI and/or Midjourney’s new video generator. - Generate music with Suno AI. - Put everything together using your favorite video editing tool. The potential is huge. This took less than an hour to complete from start to finish. Imagine what you could do with more time and a story to tell.

Hashem Al-Ghaili

29,418 次观看 • 1 年前

Sound Effects 1.0 from Sonilo is now available on fal. Generate realistic sound effects from video or text. Upload a video to get a fully synced audio track, or describe the exact sound you need with a text prompt. Generated in seconds.
0:43

Sound Effects 1.0 from Sonilo is now available on fal. Generate realistic sound effects from video or text. Upload a video to get a fully synced audio track, or describe the exact sound you need with a text prompt. Generated in seconds.

fal

21,717 次观看 • 1 个月前

Out of a 118 minute runtime, Anthony Hopkins appeared only for 16 minutes and 10 seconds. Yet his performance earned him an Oscar for Best Actor in a Leading Role.
3:11

Out of a 118 minute runtime, Anthony Hopkins appeared only for 16 minutes and 10 seconds. Yet his performance earned him an Oscar for Best Actor in a Leading Role.

Every Movie Plug

66,863 次观看 • 2 个月前

Elon Musk predicts AI will generate most of the content people consume within five to six years. "There are already people who've made AI videos using Grok Imagine and other apps that are several minutes long… and they're pretty coherent."
1:16

Elon Musk predicts AI will generate most of the content people consume within five to six years. "There are already people who've made AI videos using Grok Imagine and other apps that are several minutes long… and they're pretty coherent."

Resist the Mainstream

48,037 次观看 • 1 个月前