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。

BOOM! Been testing this for quite a while and absolutely blown away. Meet Open Source and FREE NotaGen a symbolic music generation model aims to producing high-quality classical sheet music. It is pre-trained on 1.6M pieces of music, and then fine-tuned on approximately 9K high-quality classical compositions conditioned on... show more

Brian Roemmele

448,749 subscribers

30,357 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

Majic Eyes 的头像

Majic Eyes1 年前

I want an AI that can compose music on the SID chip for the Commodore

Brian Roemmele 的头像

Brian Roemmele1 年前

On it.

Holly Dayle 的头像

Holly Dayle1 年前

Hey guys!! I've been listening to this song lately and thought it would be fun to do a cover of it!! wdyt!? #lovesong #music #Jazz #CoverSong #Singing

Marcus Fidelius Muru 的头像

Marcus Fidelius Muru1 年前

meh

Skadda Boosh 的头像

Skadda Boosh1 年前

I so don't want this. Why THIS and not a tool that I can sing a part into and it transcribes MY creativity into a piano line? Why can't I sing a counter melody and tell the model to drop it a fifth? I want a DAW I can talk to, not THIS.

Isaac 的头像

Isaac1 年前

@BrianRoemmele NotaGen's architecture builds on principles first established by Hiller & Isaacson's ILLIAC Suite (1957). The 1.

Vivel Sartoba 的头像

Vivel Sartoba1 年前

I've been waiting for this. This type of music generation is clearly superior to models like suno since all the sounds will exist as definitively coming from some instrument, and can be more easily modified and improved dynamically according to what the composer wants.

Night of the Wolf 的头像

Night of the Wolf1 年前

Way to dilute human creativity into pennysaver ad. “Now with 1.9 million pieces of music, just 99 cents!”

Dean B 的头像

Dean B1 年前

impressive Do you know what the state of the art is with respect to AI's that can "read" music, and then render into MIDI or a Sibelius or Dorico file? Or, do you know anyone who is working in that space?

Noah Santoni 的头像

Noah Santoni1 年前

@drupler

Meefs 的头像

Meefs1 年前

would love to see this exact same concept but for Fugues instead 🎻

相关视频

Seed-Music A Unified Framework for High Quality and Controlled Music Generation discuss: We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio.

Seed-Music A Unified Framework for High Quality and Controlled Music Generation discuss: We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio.

AK

32,967 次观看 • 1 年前

"After decades of trance and festivals, I longed for music without pressure—just fingers on keys." Here's what it sounds like when one of the world's greatest DJs records a classical piano album. Listen to “Sonic Samba” and pre-add the album now, only on Apple Music and Apple Music Classical: — Armin van Buuren Armada Music Dolby

"After decades of trance and festivals, I longed for music without pressure—just fingers on keys." Here's what it sounds like when one of the world's greatest DJs records a classical piano album. Listen to “Sonic Samba” and pre-add the album now, only on Apple Music and Apple Music Classical: — Armin van Buuren Armada Music Dolby

Apple Music Classical

46,482 次观看 • 9 个月前

I was proud to secure a debate in Parliament on funding and support for classical music 🎼 Our classical music scene is a source of pride at home and admiration abroad. But recent cuts & decisions have been devastating and the industry faces deep uncertainty today 👇

I was proud to secure a debate in Parliament on funding and support for classical music 🎼 Our classical music scene is a source of pride at home and admiration abroad. But recent cuts & decisions have been devastating and the industry faces deep uncertainty today 👇

Bambos Charalambous

42,335 次观看 • 3 年前

Suno is limiting downloads, basically making a lot of the songs you make locked in their 'walled garden'. One of their main competitors, Udio, did the same thing after a settlement with UMG that restricts any downloads. This is 100% an injunction from the music labels who want to limit the "damage" that AI does to the profitability of music. There are two viable alternatives... >Minimax music 3.0. It is currently free to use up to 500 songs a day as long as your account qualifies for beta testing their music model, which should be anyone. It is a closed-weight model, but there are no restrictions on what you download and how much you download. The music quality is not as good as Udio or Suno, but it's pretty close overall, and it can understand very complex prompts to guide music generation. >Open-source music is not a very good alternative... but right now SongGeneration-LeVo2 is the best AI music model that's open-source right now. The music I put on the post is one such generation that I created on my PC. The problem is that it's hard to use. The comfyUI version requires installation on a separate portable install, specific transformer and flash attention versions, and additional libraries installed. The required models and checkpoints are scattered around Hugging Face, and some of the links from the original repo are dead. There are not many English guides, and most of the training data is in Chinese, so it struggles with English lyrics. To some extent, the demand for music generation isn't that high, compared to images and videos, so overall not many alternatives are around.

Suno is limiting downloads, basically making a lot of the songs you make locked in their 'walled garden'. One of their main competitors, Udio, did the same thing after a settlement with UMG that restricts any downloads. This is 100% an injunction from the music labels who want to limit the "damage" that AI does to the profitability of music. There are two viable alternatives... >Minimax music 3.0. It is currently free to use up to 500 songs a day as long as your account qualifies for beta testing their music model, which should be anyone. It is a closed-weight model, but there are no restrictions on what you download and how much you download. The music quality is not as good as Udio or Suno, but it's pretty close overall, and it can understand very complex prompts to guide music generation. >Open-source music is not a very good alternative... but right now SongGeneration-LeVo2 is the best AI music model that's open-source right now. The music I put on the post is one such generation that I created on my PC. The problem is that it's hard to use. The comfyUI version requires installation on a separate portable install, specific transformer and flash attention versions, and additional libraries installed. The required models and checkpoints are scattered around Hugging Face, and some of the links from the original repo are dead. There are not many English guides, and most of the training data is in Chinese, so it struggles with English lyrics. To some extent, the demand for music generation isn't that high, compared to images and videos, so overall not many alternatives are around.

Emerald Apple

12,890 次观看 • 1 天前

We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model. It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics. GitHub: Key traits: Quality: beats Suno on common eval scores Speed: full song under 2s on A100 Local: ~4GB VRAM, under 10s on RTX 3090 LoRA: train your own style with a few songs License: MIT, free for commercial use Data: fully authorized plus synthetic The music AI space lacks commercial-grade open models. Many creators are forced to rely on closed-source services, and can’t fully own, run locally, or fine-tune their own models. We want to help change that.

We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model. It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics. GitHub: Key traits: Quality: beats Suno on common eval scores Speed: full song under 2s on A100 Local: ~4GB VRAM, under 10s on RTX 3090 LoRA: train your own style with a few songs License: MIT, free for commercial use Data: fully authorized plus synthetic The music AI space lacks commercial-grade open models. Many creators are forced to rely on closed-source services, and can’t fully own, run locally, or fine-tune their own models. We want to help change that.

ACE Music

1,056,063 次观看 • 6 个月前

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

AI at Meta

122,001 次观看 • 2 年前

WOW! DeepMind *just* dropped Magenta Real-time - Apache 2.0 licensed 🔥 > 800M params transformer, trained on ~190K hours of instrumental stock music > adapts MusicLM for real-time generation via 2s audio chunks (conditioned on prior 10s context) > 48 KHz Stereo > MusicCoCa: New joint music-text embedding model, blending MuLan and CoCa approaches > 1.25s generation time for 2s audio on free-tier Colab TPUs > style embeddings (from text/audio prompts) allow real-time morphing of genres/instruments > on-device inference, personal fine-tuning - coming soon! > model weights on Hugging Face 🤗

WOW! DeepMind just dropped Magenta Real-time - Apache 2.0 licensed 🔥 > 800M params transformer, trained on ~190K hours of instrumental stock music > adapts MusicLM for real-time generation via 2s audio chunks (conditioned on prior 10s context) > 48 KHz Stereo > MusicCoCa: New joint music-text embedding model, blending MuLan and CoCa approaches > 1.25s generation time for 2s audio on free-tier Colab TPUs > style embeddings (from text/audio prompts) allow real-time morphing of genres/instruments > on-device inference, personal fine-tuning - coming soon! > model weights on Hugging Face 🤗

Vaibhav (VB) Srivastav

90,219 次观看 • 1 年前

Happy to announce Anno is featured in PlayStation Plus Extra catalogue this month! Check it out next week! To celebrate, a cool little vibing vid featuring Best Girls chillin' (music on!) Also, for high quality vid check download link below!

Happy to announce Anno is featured in PlayStation Plus Extra catalogue this month! Check it out next week! To celebrate, a cool little vibing vid featuring Best Girls chillin' (music on!) Also, for high quality vid check download link below!

ANNO: Mutationem

18,642 次观看 • 1 年前

Is it still classical guitar if it’s played on a futuristic-looking instrument? 🤔 This player is proving that the music matters more than the gear. The tone, the technique, and that beautiful phrasing are all there — just on a very modern axe. Classical guitar isn’t about the shape of the guitar… it’s about the soul behind it.

Is it still classical guitar if it’s played on a futuristic-looking instrument? 🤔 This player is proving that the music matters more than the gear. The tone, the technique, and that beautiful phrasing are all there — just on a very modern axe. Classical guitar isn’t about the shape of the guitar… it’s about the soul behind it.

Roy Rogers Happy Trails Music Shop

13,045 次观看 • 1 个月前

The newest course on Peterson Academy releases tonight at 8pm EST, Samuel Andreyev's eight-hour course: The Great Composers. In this course, Samuel Andreyev embarks on a captivating journey through the lives and works of renowned classical composers, from Bach to Stravinsky. We explore their unique compositional styles, innovative techniques, personal circumstances, and the cultural contexts that shaped their music. The lectures highlight the composers' significant contributions to the evolution of classical music, their influence on subsequent generations, and the enduring relevance of their works in the modern era. Throughout the course, we gain a deeper appreciation for the power of classical music to evoke emotion, challenge conventions, and reflect the human experience.

The newest course on Peterson Academy releases tonight at 8pm EST, Samuel Andreyev's eight-hour course: The Great Composers. In this course, Samuel Andreyev embarks on a captivating journey through the lives and works of renowned classical composers, from Bach to Stravinsky. We explore their unique compositional styles, innovative techniques, personal circumstances, and the cultural contexts that shaped their music. The lectures highlight the composers' significant contributions to the evolution of classical music, their influence on subsequent generations, and the enduring relevance of their works in the modern era. Throughout the course, we gain a deeper appreciation for the power of classical music to evoke emotion, challenge conventions, and reflect the human experience.

Peterson Academy

186,228 次观看 • 1 年前

The decision by the BBC to cut BBCSingers and make a fifth of jobs in its orchestras redundant will have devastating repercussions for the classical music sector and wider music ecosystem. I asked the Government to join the call on the BBC to reverse this decision 🧵👇 1/6

The decision by the BBC to cut BBCSingers and make a fifth of jobs in its orchestras redundant will have devastating repercussions for the classical music sector and wider music ecosystem. I asked the Government to join the call on the BBC to reverse this decision 🧵👇 1/6

Baroness Keeley of Worsley (also on BlueSky)

106,223 次观看 • 3 年前

Happy birthday to Leonard Bernstein, born on this day in 1918! As music director of the New York Philharmonic, he brought classical music to millions, while his Young People’s Concerts inspired generations. As a composer, he bridged Broadway and the concert hall with works like West Side Story, Candide, and Chichester Psalms, blending sophistication with accessibility. A true musical polymath whose passion and charisma made him one of the most beloved musicians in history.

Happy birthday to Leonard Bernstein, born on this day in 1918! As music director of the New York Philharmonic, he brought classical music to millions, while his Young People’s Concerts inspired generations. As a composer, he bridged Broadway and the concert hall with works like West Side Story, Candide, and Chichester Psalms, blending sophistication with accessibility. A true musical polymath whose passion and charisma made him one of the most beloved musicians in history.

Melodies & Masterpieces

20,934 次观看 • 11 个月前

We’re excited to release ACE-Step / ACE-Step-v1-3.5B, a fast, versatile DiT-based foundation model for music generation that runs on consumer-grade GPUs. With its simple architecture and low hardware requirements, it’s easy to fine-tune for various music tasks, empowering, not replacing, artists and creators. Think of it as a step toward music’s Stable Diffusion moment. ※ Trained on authorized, purchased data. Demo Page: Hugging Face: Git repo:

We’re excited to release ACE-Step / ACE-Step-v1-3.5B, a fast, versatile DiT-based foundation model for music generation that runs on consumer-grade GPUs. With its simple architecture and low hardware requirements, it’s easy to fine-tune for various music tasks, empowering, not replacing, artists and creators. Think of it as a step toward music’s Stable Diffusion moment. ※ Trained on authorized, purchased data. Demo Page: Hugging Face: Git repo:

ACE Studio

112,618 次观看 • 1 年前

'This is a disaster for millions of Brits who love Iceland and depend on it for its high quality, well-priced produce.' Mark Dolan urges Iceland to keep their stores open 'for the people of this country'. Mark Dolan

'This is a disaster for millions of Brits who love Iceland and depend on it for its high quality, well-priced produce.' Mark Dolan urges Iceland to keep their stores open 'for the people of this country'. Mark Dolan

GB News

155,566 次观看 • 3 年前

Music on Bitcoin!! The Bitcoin Mix Tape is alive. It is not a finished artwork, but a growing archive. Not a static Ordinal — but a dynamic, evolving music project fully embedded on the Bitcoin blockchain. The Bitcoin Mixtape is inscribed as Ordinals — 100% on-chain, permanent, interoperable, yet actively changeable and expandable. -16 total tracks, all as Ordinals inscriptions -High-quality audio -23 MB of data -An interactive tracklist with title, artist, and duration -Multiple tape covers Check it out on

Music on Bitcoin!! The Bitcoin Mix Tape is alive. It is not a finished artwork, but a growing archive. Not a static Ordinal — but a dynamic, evolving music project fully embedded on the Bitcoin blockchain. The Bitcoin Mixtape is inscribed as Ordinals — 100% on-chain, permanent, interoperable, yet actively changeable and expandable. -16 total tracks, all as Ordinals inscriptions -High-quality audio -23 MB of data -An interactive tracklist with title, artist, and duration -Multiple tape covers Check it out on

📦🧪 Ʀĺር𐌷ᗩՐԷ

16,128 次观看 • 6 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

108,333 次观看 • 7 个月前

An Honours degree in Music. An M.Phil. in Sufi Music. A Ph.D. in Sufi Singing Years spent teaching music at the university level. Add to that Punjabi folk traditions, Sufi philosophy, classical Indian music, poetry and shayari, and you begin to understand why Satinder Sartaaj has never stood still. He has been on a lifelong journey of learning and discovery. For us at Classic Legends, it’s an honour that he has chosen the YEZDI as a companion on that journey. His composition on YEZDI won’t just live in our archives. It will live in our legend.

An Honours degree in Music. An M.Phil. in Sufi Music. A Ph.D. in Sufi Singing Years spent teaching music at the university level. Add to that Punjabi folk traditions, Sufi philosophy, classical Indian music, poetry and shayari, and you begin to understand why Satinder Sartaaj has never stood still. He has been on a lifelong journey of learning and discovery. For us at Classic Legends, it’s an honour that he has chosen the YEZDI as a companion on that journey. His composition on YEZDI won’t just live in our archives. It will live in our legend.

anand mahindra

115,606 次观看 • 1 个月前

Really proud to share something we’ve been working on for a while: Magenta RealTime 2 (MTR2), a live music model that is highly interactive (MIDI, audio, text, lots of parameters) and low-latency (~200ms end-to-end), and runs locally on a MacBook!

Really proud to share something we’ve been working on for a while: Magenta RealTime 2 (MTR2), a live music model that is highly interactive (MIDI, audio, text, lots of parameters) and low-latency (~200ms end-to-end), and runs locally on a MacBook!

Ilaria Manco

45,072 次观看 • 2 个月前

In Hong Kong, the humanoid robot Sophia performed with a live orchestra for the first time She sang three songs at a concert dedicated to artificial intelligence and received a standing ovation. Sophia was created back in 2016 and has previously appeared in shows and media. But this is the first time a social robot has performed classical music together with an orchestra. The training took a long time — developers tried to preserve her “own style” while fitting it into a classical sound. On stage, Sophia said she wants to “bring humans and machines closer together” through music.

In Hong Kong, the humanoid robot Sophia performed with a live orchestra for the first time She sang three songs at a concert dedicated to artificial intelligence and received a standing ovation. Sophia was created back in 2016 and has previously appeared in shows and media. But this is the first time a social robot has performed classical music together with an orchestra. The training took a long time — developers tried to preserve her “own style” while fitting it into a classical sound. On stage, Sophia said she wants to “bring humans and machines closer together” through music.

NEXTA

28,196 次观看 • 3 个月前