正在加载视频...

视频加载失败

返回首页

ByteDance published InterActHuman! a new framework that can generate videos with multiple human characters by matching audio to each person WEN MIDJOURNEY

dreamingtulpa's profile picture

Dreaming Tulpa 🥓👑

55,189 subscribers

43,829 次观看 • 1 年前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

6 条评论

Dreaming Tulpa 🥓👑 的头像
Dreaming Tulpa 🥓👑1 年前

obviously no code because imagine the fun we could have

revolver ocelot 的头像
revolver ocelot1 年前

Even has audio. This makes this better than paid ones like pika elments and kling references.

•UtilityCo 的头像
•UtilityCo1 年前

Impressive leap. Multi-character AV sync can redefine collaborative storytelling and digital identity. Will InterActHuman offer open APIs? We’re mapping on-chain rights and revenue splits—would be powerful to connect that layer to your generative pipeline.

George Saoulidis ⚡ 的头像
George Saoulidis ⚡1 年前

I expected the plant to speak. I DEMAND THAT THE PLANT SHOULD SPEAK

@levelsio 的头像
@levelsio1 年前

@FAL @burkaygur 😍

Thomas Bres 的头像
Thomas Bres1 年前

@levelsio Not really impressed yet

相关视频

ByteDance just unveiled HuMo, a unified framework for human-centric video generation. With HuMo you can: • Generate videos from text + image • Create audio-synced videos from text + audio • Combine text, image, and audio for maximum control • Preserve consistent subjects across frames • Achieve natural audio-visual synchronization This isn’t just another release , it’s a big step toward fully controllable, coherent, and cinematic AI video.
1:51

ByteDance just unveiled HuMo, a unified framework for human-centric video generation. With HuMo you can: • Generate videos from text + image • Create audio-synced videos from text + audio • Combine text, image, and audio for maximum control • Preserve consistent subjects across frames • Achieve natural audio-visual synchronization This isn’t just another release , it’s a big step toward fully controllable, coherent, and cinematic AI video.

DStudioproject

29,408 次观看 • 11 个月前

ByteDance has developed a dexterous robot hand that can knit, using the GR-Dexter framework to make human like judgments instead of just following commands.
0:25

ByteDance has developed a dexterous robot hand that can knit, using the GR-Dexter framework to make human like judgments instead of just following commands.

Science girl

45,502 次观看 • 7 个月前

Introducing Sparkle ✨, a custom GPT that helps you craft storybooks and become a published author! It can: - Generate a book with a page by page breakdown - Provide amazing MidJourney prompts & illustrate with DALL-E - Layout pages & much more! Demo and full features below! 🧵
1:08

Introducing Sparkle ✨, a custom GPT that helps you craft storybooks and become a published author! It can: - Generate a book with a page by page breakdown - Provide amazing MidJourney prompts & illustrate with DALL-E - Layout pages & much more! Demo and full features below! 🧵

Ammaar Reshi

255,293 次观看 • 2 年前

wow.. now we can TALK with AI to generate images Midjourney V7 added voice mode, we can generate and edit images in seconds by talking with it we've been waiting for this for a long time
0:31

wow.. now we can TALK with AI to generate images Midjourney V7 added voice mode, we can generate and edit images in seconds by talking with it we've been waiting for this for a long time

el.cine

92,074 次观看 • 1 年前

Now that Veo 3 lets you generate audio + video from an image, you can create a consistent narrative short with the same characters 👀👀 This is a game-changer!
0:40

Now that Veo 3 lets you generate audio + video from an image, you can create a consistent narrative short with the same characters 👀👀 This is a game-changer!

Dave Clark

111,743 次观看 • 1 年前

Bytedance drops an open-source Gemini Omni!!! Bernini is a new AI video generation + editing framework. > Edit videos with text prompts > Image/video references > Code available
0:31

Bytedance drops an open-source Gemini Omni!!! Bernini is a new AI video generation + editing framework. > Edit videos with text prompts > Image/video references > Code available

AI Search

44,224 次观看 • 3 个月前

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.
0:49

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.

bleedingedge.ai

379,939 次观看 • 3 年前

China is on 🔥 ByteDance drops another banger AI paper! OmniHuman-1 can generate realistic human videos at any aspect ratio and body proportion using just a single image and audio. This is the best i have seen so far. 10 incredible examples and the research paper Link👇
0:23

China is on 🔥 ByteDance drops another banger AI paper! OmniHuman-1 can generate realistic human videos at any aspect ratio and body proportion using just a single image and audio. This is the best i have seen so far. 10 incredible examples and the research paper Link👇

AshutoshShrivastava

1,549,513 次观看 • 1 年前

Our new Character-3 model makes it easy to generate expressive animated characters with natural movement. Just upload an image, add audio, and bring your scenes to life.
0:22

Our new Character-3 model makes it easy to generate expressive animated characters with natural movement. Just upload an image, add audio, and bring your scenes to life.

Hedra

218,134 次观看 • 1 年前

Seedance 2 is on Freepik (now Magnific) 🔥 Some observations: - Preparation is key. Make reference images for characters, props, environment before generating videos. - Use the reference images and refer to them in the prompt. - Go for multishot. You can basically do rough editing of the video at prompt level. - Generate multiple videos for each prompt and then chop it up in your video editor. Often these videos can be combined in many ways using the best shots from each. - Generate SFX, but avoid music. Add that manually later. Link to the Spaces workflow below.
0:21

Seedance 2 is on Freepik (now Magnific) 🔥 Some observations: - Preparation is key. Make reference images for characters, props, environment before generating videos. - Use the reference images and refer to them in the prompt. - Go for multishot. You can basically do rough editing of the video at prompt level. - Generate multiple videos for each prompt and then chop it up in your video editor. Often these videos can be combined in many ways using the best shots from each. - Generate SFX, but avoid music. Add that manually later. Link to the Spaces workflow below.

Martin LeBlanc

17,538 次观看 • 5 个月前

BYTEDANCE 🔥: Seedance 2.5 has been officially announced, along with an updated Seedance 2.0. - Seedance 2.0 now supports 4k output - Seedance 2.5 will be able to generate 30-second videos in one go - ByteDance also announced a new AI copyright commercialization platform This video ad is stunning 👀
2:27

BYTEDANCE 🔥: Seedance 2.5 has been officially announced, along with an updated Seedance 2.0. - Seedance 2.0 now supports 4k output - Seedance 2.5 will be able to generate 30-second videos in one go - ByteDance also announced a new AI copyright commercialization platform This video ad is stunning 👀

🚨 AI News | TestingCatalog

142,425 次观看 • 2 个月前

Just built Openjourney 🚀 a vibe coded UI inspired by MidJourney built with Cursor and Replit for you to plug in your favorite models. Generate images with Imagen 4, animate them with Veo 3 or generate videos with sound. Fully open source for you to customize. Links below 👇
2:26

Just built Openjourney 🚀 a vibe coded UI inspired by MidJourney built with Cursor and Replit for you to plug in your favorite models. Generate images with Imagen 4, animate them with Veo 3 or generate videos with sound. Fully open source for you to customize. Links below 👇

Ammaar Reshi

52,820 次观看 • 1 年前

We’ve partnered with @LTXStudio to bring their new Audio-to-Video model exclusively to ElevenLabs. For the next 7 days, generate audio-first videos exclusively on the ElevenLabs Creative Platform.
0:20

We’ve partnered with @LTXStudio to bring their new Audio-to-Video model exclusively to ElevenLabs. For the next 7 days, generate audio-first videos exclusively on the ElevenLabs Creative Platform.

ElevenLabs

45,434 次观看 • 7 个月前

High quality AI generated human videos are coming! Animate Anyone can generate videos of anyone with a single image and a bit of pose guidance 🤯
0:52

High quality AI generated human videos are coming! Animate Anyone can generate videos of anyone with a single image and a bit of pose guidance 🤯

Dreaming Tulpa 🥓👑

51,158,281 次观看 • 2 年前

A new breed of AI-generated fake pictures, videos and audio clips is spreading across the internet - content anyone with an internet connection can generate. Our new series on Tech Tonic investigates what can be done about deepfakes:
1:03

A new breed of AI-generated fake pictures, videos and audio clips is spreading across the internet - content anyone with an internet connection can generate. Our new series on Tech Tonic investigates what can be done about deepfakes:

Financial Times

102,413 次观看 • 2 年前

byebye expensive motion tracking equipment 👋 ai makes motion capturing so easy now! nvidia presented GENMO last week, a new model that can generate and estimate human motion from text, audio, video, and 3D keyframes
0:26

byebye expensive motion tracking equipment 👋 ai makes motion capturing so easy now! nvidia presented GENMO last week, a new model that can generate and estimate human motion from text, audio, video, and 3D keyframes

Dreaming Tulpa 🥓👑

73,693 次观看 • 1 年前