正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

This is wild 🤯 We finally have an open-source music generation model that rocks 🚀

Victor M

23,363 subscribers

248,740 次观看 • 1 年前 •via X (Twitter)

音乐科学技术

Anya Rossi• Live Now

Private livecam show

11 条评论

Yorkie 的头像

Yorkie1 年前

Would love a huggingface space for this :D

Solar Heavy 的头像

Solar Heavy1 年前

check this edm guitar track out

Octavi Grau 的头像

Octavi Grau1 年前

And it's chinese!

Vivek Naskar 的头像

Vivek Naskar1 年前

Hopefully, you guys create a space for trying this.

Simon 的头像

Simon1 年前

@OliDietzel I'll try to see if Deepseek R1 can create a oneclick Installer for this. Right now I try the same with Janus-Pro. ✌️ It will probably fail, but I wonder... 😬

Victor M 的头像

Victor M1 年前

@OliDietzel With the right context maybe it could work yes

Simon 的头像

Simon1 年前

@OliDietzel Ps. nice songs you've created here! 🥳

Victor M 的头像

Victor M1 年前

@OliDietzel it's from their demos page :')

Rina | AGEofLLMs 的头像

Rina | AGEofLLMs1 年前

Wow thays amazing!

Akash Bajwa 的头像

Akash Bajwa1 年前

@thisisneer

Yvette Pan 的头像

Yvette Pan1 年前

This also by a Chinese researcher 👏

相关视频

Google Genie 3 just got its biggest open-source rival 🤯 LingBot-World is an open-source world model that generates playable environments in real-time. → Built on Alibaba’s Wan2.2 → 10 minutes of stable generation → 16fps real-time interaction 100% Open Source.

Google Genie 3 just got its biggest open-source rival 🤯 LingBot-World is an open-source world model that generates playable environments in real-time. → Built on Alibaba’s Wan2.2 → 10 minutes of stable generation → 16fps real-time interaction 100% Open Source.

Alvaro Cintas

1,059,115 次观看 • 5 个月前

Finally! A Text-to-SQL tool that actually works! Vanna is an open-source RAG framework for complex Text-to-SQL generation. It manages dynamic data and allows custom RAG model training for greater accuracy. 100% open-source.

Finally! A Text-to-SQL tool that actually works! Vanna is an open-source RAG framework for complex Text-to-SQL generation. It manages dynamic data and allows custom RAG model training for greater accuracy. 100% open-source.

Akshay 🚀

168,600 次观看 • 1 年前

Stable Diffusion Moment of Audio?? Ace-Step Audio Model just dropped and is now natively supported in ComfyUI. ACE-Step is an open-source music generation model jointly developed by ACE Studio and StepFun.

Stable Diffusion Moment of Audio?? Ace-Step Audio Model just dropped and is now natively supported in ComfyUI. ACE-Step is an open-source music generation model jointly developed by ACE Studio and StepFun.

ComfyUI

23,495 次观看 • 1 年前

We have released our LFM2-350M based TTS model as open source 🚀 We have also released many different FT models. GPU Platform: Hyperbolic Data: Emilia + Emilia Yodas(EN) LLM Model: LFM2-350M Disk and Space: Hugging Face I'm very happy to have released this model as open source. Many thanks to Vyvo Smart Chain #opensource #speech #tts #huggingface #lfm #gpu

We have released our LFM2-350M based TTS model as open source 🚀 We have also released many different FT models. GPU Platform: Hyperbolic Data: Emilia + Emilia Yodas(EN) LLM Model: LFM2-350M Disk and Space: Hugging Face I'm very happy to have released this model as open source. Many thanks to Vyvo Smart Chain #opensource #speech #tts #huggingface #lfm #gpu

Kadir Nar

39,109 次观看 • 11 个月前

What is Alpaca Network's Modelz Platform? Our core contributor Joaquim Miro breaks it down: ✅Tokenize any open-source AI model in seconds 🚀Launch an IMO (Initial Model Offering) 💸Earn from model usage, fully on-chain The AI model layer is finally decentralized

What is Alpaca Network's Modelz Platform? Our core contributor Joaquim Miro breaks it down: ✅Tokenize any open-source AI model in seconds 🚀Launch an IMO (Initial Model Offering) 💸Earn from model usage, fully on-chain The AI model layer is finally decentralized

Alpaca Network

42,564 次观看 • 1 年前

🎥 Frustrated by Sora's credit limits? Still waiting for Veo 2? 🚀 Open-source video DiTs are actually on par. We introduce FastVideo, an open-source stack to support fast video generation for SoTA open models. We have supported Mochi and Hunyuan, 8x faster inference, 720P 5-second video in 62 seconds.

🎥 Frustrated by Sora's credit limits? Still waiting for Veo 2? 🚀 Open-source video DiTs are actually on par. We introduce FastVideo, an open-source stack to support fast video generation for SoTA open models. We have supported Mochi and Hunyuan, 8x faster inference, 720P 5-second video in 62 seconds.

Hao AI Lab

69,735 次观看 • 1 年前

It only took a week for an open source interactive world model to release🤯

It only took a week for an open source interactive world model to release🤯

noah

385,879 次观看 • 11 个月前

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Exciting News from Open-Sora! 🚀 They've just made the ENTIRE suite of their video-generation model open source! Dive into the world of cutting-edge AI with access to model weights, comprehensive training source code, and detailed architecture insights. Start building your dream video-generation model today! Check it out 👉

Yang You

245,742 次观看 • 2 年前

We might have a new top open-source music generator. > Unified acoustic-token pipeline > Full-song generation > Text + lyric control for style, mood, vocals

We might have a new top open-source music generator. > Unified acoustic-token pipeline > Full-song generation > Text + lyric control for style, mood, vocals

⚡AI Search⚡

13,849 次观看 • 2 个月前

This is wild 🤯 AO NISHIKAWA is the FUTURE 🚀

This is wild 🤯 AO NISHIKAWA is the FUTURE 🚀

Thrasher Magazine

30,048 次观看 • 3 个月前

ACE-Step-v1.5(2B) is a new open-source music AI model that runs locally in #ComfyUI :) * Only needs ~4GB VRAM * MIT licence * Done in 8 seconds! * Have a listen :p

ACE-Step-v1.5(2B) is a new open-source music AI model that runs locally in #ComfyUI :) * Only needs ~4GB VRAM * MIT licence * Done in 8 seconds! * Have a listen :p

Nerdy Rodent 🐀🤓💻🪐🚴

11,663 次观看 • 5 个月前

We launched livekit-wakeword, an open-source library that lets you train a custom wake word model from scratch with a single command. It handles synthetic data generation, augmentation, training, and ONNX export all in one shot.

We launched livekit-wakeword, an open-source library that lets you train a custom wake word model from scratch with a single command. It handles synthetic data generation, augmentation, training, and ONNX export all in one shot.

LiveKit

10,104 次观看 • 3 个月前

We believe an open approach is the right one for the development of today's Al models. Today, we’re releasing Llama 2, the next generation of Meta’s open source Large Language Model, available for free for research & commercial use. Details ➡️

We believe an open approach is the right one for the development of today's Al models. Today, we’re releasing Llama 2, the next generation of Meta’s open source Large Language Model, available for free for research & commercial use. Details ➡️

AI at Meta

1,234,668 次观看 • 3 年前

🚨🚨 REMARKABLE FOOTAGE🚨🚨 NEW WILD PRACTICE FOOTAGE FROM THE 1924 NOTRE DAME FOOTBALL TEAM. 🤯🤯🤯 IT IS CRAZY THAT WE HAVE THIS FOOTAGE.

🚨🚨 REMARKABLE FOOTAGE🚨🚨 NEW WILD PRACTICE FOOTAGE FROM THE 1924 NOTRE DAME FOOTBALL TEAM. 🤯🤯🤯 IT IS CRAZY THAT WE HAVE THIS FOOTAGE.

MLFootball

833,193 次观看 • 9 个月前

🚨🚨REMARKABLE FOOTAGE🚨🚨 NEW WILD FOOTAGE FROM THE CHICAGO #BEARS GAME IN THE YEAR 1933. They were running some wild plays🤯🤯🤯 IT IS INSANE THAT WE HAVE THIS FOOTAGE.

🚨🚨REMARKABLE FOOTAGE🚨🚨 NEW WILD FOOTAGE FROM THE CHICAGO #BEARS GAME IN THE YEAR 1933. They were running some wild plays🤯🤯🤯 IT IS INSANE THAT WE HAVE THIS FOOTAGE.

MLFootball

1,888,961 次观看 • 8 个月前

In an AI world, effort is no longer the bottleneck—ideas are. Open-source AI enables anyone to have access to build anything they want without depending on the one-sided gates that closed-source offers. This is amplified by the open innovation that open-source development enables.

In an AI world, effort is no longer the bottleneck—ideas are. Open-source AI enables anyone to have access to build anything they want without depending on the one-sided gates that closed-source offers. This is amplified by the open innovation that open-source development enables.

Sentient

17,392 次观看 • 5 个月前

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

ComfyUI

108,130 次观看 • 6 个月前