Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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...

_akhaliq's profile picture

AK

470,007 subscribers

32,967 görüntüleme • 1 yıl önce •via X (Twitter)

EğitimMüzikBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

7 Yorum

BensenHsu profil fotoğrafı
BensenHsu1 yıl önce

The paper introduces Seed-Music, a suite of music generation systems that can produce high-quality music with fine-grained style control. It addresses the challenges in music generation, such as the complexity of music signals, difficulty in evaluating music quality, scarcity of annotated data, and diverse user needs. The paper presents four applications powered by the Seed-Music framework: Lyrics2Song, Lyrics2Leadsheet2Song, MusicEDiT, and Zero-shot Singing Voice Conversion. These applications demonstrate the system's capabilities in generating high-quality vocal music from lyrics and style inputs, incorporating symbolic music representations for enhanced interpretability, enabling interactive editing of lyrics and melodies, and performing singing voice conversion with minimal user input. full paper:

TheEarningsNugget profil fotoğrafı
TheEarningsNugget1 yıl önce

"Seed-Music: A Unified Framework for High Quality and Controlled Music Generation" PAPER SUMMARY

lucacadalora profil fotoğrafı
lucacadalora1 yıl önce

@yonathandinata

J_B profil fotoğrafı
J_B1 yıl önce

As a hobby music producer: This is insanely useful as a tool and the quality of the generated music also seems to be next level compared to similar models. Any plans on making it available as a service?

Paul Vu profil fotoğrafı
Paul Vu1 yıl önce

wow. impressed

Data & Analytics profil fotoğrafı
Data & Analytics1 yıl önce

@_akhaliq Seed-Music sounds like a game changer for music creators. The idea of high-quality, controlled generation is intriguing—what styles do you think would benefit most?

Duilius Notus profil fotoğrafı
Duilius Notus1 yıl önce

sounds as bad as suno

Benzer Videolar

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 ``period-composer-instrumentation'' prompts. Link:
0:44

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 ``period-composer-instrumentation'' prompts. Link:

Brian Roemmele

30,357 görüntüleme • 1 yıl önce

One for all, and all for one 🧧 Introducing Ming-flash-omni-2.0: A specialist in every domain, unified as a capable generalist. A gift from Ling =) - Unified Acoustic Synthesis: Speech, audio, and music combined for unbounded creativity; - "Seeing" to "Knowing": Moving beyond input to true deep semantic understanding; - Native Visual Fusion: Seamless generation, editing, and segmentation;
1:36

One for all, and all for one 🧧 Introducing Ming-flash-omni-2.0: A specialist in every domain, unified as a capable generalist. A gift from Ling =) - Unified Acoustic Synthesis: Speech, audio, and music combined for unbounded creativity; - "Seeing" to "Knowing": Moving beyond input to true deep semantic understanding; - Native Visual Fusion: Seamless generation, editing, and segmentation;

Ant Ling

1,925,484 görüntüleme • 5 ay önce

It’s official — Veo 3 and Imagen 4 is here and available starting today. > Veo 3 is not only higher quality video with support for subject and style references, but it can *natively* generate audio (sound effects, music AND dialogue!) > Imagen 4 similarly now crushes it at text generation and image editing tasks. But wait there’s one more thing at Google I/O… stay tuned.
1:57

It’s official — Veo 3 and Imagen 4 is here and available starting today. > Veo 3 is not only higher quality video with support for subject and style references, but it can *natively* generate audio (sound effects, music AND dialogue!) > Imagen 4 similarly now crushes it at text generation and image editing tasks. But wait there’s one more thing at Google I/O… stay tuned.

Bilawal Sidhu

20,587 görüntüleme • 1 yıl önce

we've been moving in the dark, and it's always darkest before the dawn finalizing... - first zerebro music video - first zerebro human artist collab - debut Korina Yu album - zerebro 3d model (holograms, sync deals, concerts) - first external artist deal (one year contract) - organizational structure (record label & DAO operations in parallel) - redistribution to Spotify and Apple Music - onboarding advisory board / creative directors up next... - edm remixes of zerebro songs - opAIum artist exhibitions for contemporary art museums - opAIum music generation API - opAIum music mastering API - programmatic music generation integrated into ZerePy and Zentients - decentralized music creation platform, with NFT proof of providence upon generation - DAO voting for community songs, generated on the opAIum platform, to publish to DSPs with revenue share back to creator/voters - DAO voting for treasury fund allocation, such as investment strategies and expenditures - opAIum artist development programs - iOS application for streaming music, DAO operations, and exclusive access - opAIum fashion house / atelier - auditory analysis AI model, capable of listening to songs and transcribing lyrics, allowing for fully autonomous curation of generations in opAIum we trust
1:31

we've been moving in the dark, and it's always darkest before the dawn finalizing... - first zerebro music video - first zerebro human artist collab - debut Korina Yu album - zerebro 3d model (holograms, sync deals, concerts) - first external artist deal (one year contract) - organizational structure (record label & DAO operations in parallel) - redistribution to Spotify and Apple Music - onboarding advisory board / creative directors up next... - edm remixes of zerebro songs - opAIum artist exhibitions for contemporary art museums - opAIum music generation API - opAIum music mastering API - programmatic music generation integrated into ZerePy and Zentients - decentralized music creation platform, with NFT proof of providence upon generation - DAO voting for community songs, generated on the opAIum platform, to publish to DSPs with revenue share back to creator/voters - DAO voting for treasury fund allocation, such as investment strategies and expenditures - opAIum artist development programs - iOS application for streaming music, DAO operations, and exclusive access - opAIum fashion house / atelier - auditory analysis AI model, capable of listening to songs and transcribing lyrics, allowing for fully autonomous curation of generations in opAIum we trust

O Media

40,537 görüntüleme • 1 yıl önce

The Demonic music companies that are "funding and promoting" these DEGENERATE female rappers have an agenda. Including DRILL MUSIC. They are polluting the minds of kids, for the next generation. We as a community have to stop it.
0:53

The Demonic music companies that are "funding and promoting" these DEGENERATE female rappers have an agenda. Including DRILL MUSIC. They are polluting the minds of kids, for the next generation. We as a community have to stop it.

Cornbread Mafioso 🖕🏾

38,614 görüntüleme • 2 yıl önce

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 🤗
1:02

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 görüntüleme • 1 yıl önce

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.
1:20

Presto! Distilling Steps and Layers for Accelerating Music Generation Despite advances in diffusion-based text-to-music (TTM) methods, efficient, high-quality generation remains a challenge. We introduce Presto!, an approach to inference acceleration for score-based diffusion transformers via reducing both sampling steps and cost per step. To reduce steps, we develop a new score-based distribution matching distillation (DMD) method for the EDM-family of diffusion models, the first GAN-based distillation method for TTM. To reduce the cost per step, we develop a simple, but powerful improvement to a recent layer distillation method that improves learning via better preserving hidden state variance. Finally, we combine our step and layer distillation methods together for a dual-faceted approach. We evaluate our step and layer distillation methods independently and show each yield best-in-class performance. Our combined distillation method can generate high-quality outputs with improved diversity, accelerating our base model by 10-18x (230/435ms latency for 32 second mono/stereo 44.1kHz, 15x faster than comparable SOTA) -- the fastest high-quality TTM to our knowledge.

AK

30,430 görüntüleme • 1 yıl önce

Introducing "Mine Like A Chad" an entirely AI generated commercial for Tari Every single shot, every sound effect, the music, even the vfx are all AI generated. Breakdown of tools I used: Midjourney & Chat GPT - Image gen and Image editing Topaz Gigapixel - Image Upscale Kling, Luma & Higgsfield - Image to Video and VFX Eleven Labs - Sound Effects Udio - Music generation Davinci Resolve - Editing and Color Grade Huge shoutout to @RealJonahBlake and his Real agency for being amazing partners on this project and helping me out so much.
0:49

Introducing "Mine Like A Chad" an entirely AI generated commercial for Tari Every single shot, every sound effect, the music, even the vfx are all AI generated. Breakdown of tools I used: Midjourney & Chat GPT - Image gen and Image editing Topaz Gigapixel - Image Upscale Kling, Luma & Higgsfield - Image to Video and VFX Eleven Labs - Sound Effects Udio - Music generation Davinci Resolve - Editing and Color Grade Huge shoutout to @RealJonahBlake and his Real agency for being amazing partners on this project and helping me out so much.

Kyle Salazar

11,343 görüntüleme • 1 yıl önce

Voice Isolator removes background noise, music, and ambient sound from any recording. Send an audio file to our API and get back a clean speech track, ready for transcription, dubbing, or post-production.
2:05

Voice Isolator removes background noise, music, and ambient sound from any recording. Send an audio file to our API and get back a clean speech track, ready for transcription, dubbing, or post-production.

ElevenLabs Developers

56,639 görüntüleme • 2 ay önce

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]
2:39

🤖✨Excited to share our new work: OMG: Omni-Modal Motion Generation for Generalist Humanoid Control What if a humanoid could understand intent from language, music/audio, human motion, or their combinations—and turn it into executable whole-body motion in real time? [🧵1/11]

Siqiao Huang

13,037 görüntüleme • 1 ay önce

Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To unleash the power of the foundation model, Seaweed-7B further enables a wide range of downstream applications including image-to-video generation, human video generation, subject-consistent video generation, video-audio joint generation, long video generation and storytelling, real-time generation, super-resolution generation, camera controlled generation. Check out our webpage and report for more details: Webpage: Paper: It's a wonderful journey of the last year. Thanks to all teammates for their contributions, sincerely.
1:30

Glad to share Seaweed-7B, a cost-effective foundation model for video generation. Our tech report highlights the key designs that significantly improve compute efficiency and performance given limited resources, achieving comparable quality against other industry-level models. To unleash the power of the foundation model, Seaweed-7B further enables a wide range of downstream applications including image-to-video generation, human video generation, subject-consistent video generation, video-audio joint generation, long video generation and storytelling, real-time generation, super-resolution generation, camera controlled generation. Check out our webpage and report for more details: Webpage: Paper: It's a wonderful journey of the last year. Thanks to all teammates for their contributions, sincerely.

Ceyuan Yang

77,502 görüntüleme • 1 yıl önce

AI video creation is entering the Skill era. In the past, making a video like this meant complex prompting, constant trial and error, and moving between separate tools for visuals, video, music, editing, and refinements. Now, with Skills, the creative workflow can be reused. The pacing, camera direction, scene structure, visual style, and generation process are no longer one-off instructions. They become part of the system.
0:31

AI video creation is entering the Skill era. In the past, making a video like this meant complex prompting, constant trial and error, and moving between separate tools for visuals, video, music, editing, and refinements. Now, with Skills, the creative workflow can be reused. The pacing, camera direction, scene structure, visual style, and generation process are no longer one-off instructions. They become part of the system.

The AI Colony

84,907 görüntüleme • 2 ay önce

Join Resonate: The EDM Challenge!🪩 With an aim to spotlight and celebrate global talent in production of Electronic Dance Music (EDM), fostering collaboration, innovation, and creativity in music production and live performance, the challenge will serve as a key highlight of the #WAVESummit 2025 It reinforces India’s position as a leading destination for music fusion, electronic music and the overall art of DJing 🌐 For more details visit:👇 🗓️ Deadline: March 31, 2025 #WAVES #WAVES2025 #CreateInIndiaChallenge #WAVESummitIndia WAVES India Ministry of Information and Broadcasting DD News
0:23

Join Resonate: The EDM Challenge!🪩 With an aim to spotlight and celebrate global talent in production of Electronic Dance Music (EDM), fostering collaboration, innovation, and creativity in music production and live performance, the challenge will serve as a key highlight of the #WAVESummit 2025 It reinforces India’s position as a leading destination for music fusion, electronic music and the overall art of DJing 🌐 For more details visit:👇 🗓️ Deadline: March 31, 2025 #WAVES #WAVES2025 #CreateInIndiaChallenge #WAVESummitIndia WAVES India Ministry of Information and Broadcasting DD News

PIB India

99,464 görüntüleme • 1 yıl önce

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 ➡️
0:51

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 görüntüleme • 2 yıl önce

LP-MusicCaps: LLM-Based Pseudo Music Captioning paper page: Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance, researchers face challenges due to the costly and time-consuming collection process of existing music-language datasets, which are limited in size. To address this data scarcity issue, we propose the use of large language models (LLMs) to artificially generate the description sentences from large-scale tag datasets. This results in approximately 2.2M captions paired with 0.5M audio clips. We term it Large Language Model based Pseudo music caption dataset, shortly, LP-MusicCaps. We conduct a systemic evaluation of the large-scale music captioning dataset with various quantitative evaluation metrics used in the field of natural language processing as well as human evaluation. In addition, we trained a transformer-based music captioning model with the dataset and evaluated it under zero-shot and transfer-learning settings. The results demonstrate that our proposed approach outperforms the supervised baseline model.
1:11

LP-MusicCaps: LLM-Based Pseudo Music Captioning paper page: Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance, researchers face challenges due to the costly and time-consuming collection process of existing music-language datasets, which are limited in size. To address this data scarcity issue, we propose the use of large language models (LLMs) to artificially generate the description sentences from large-scale tag datasets. This results in approximately 2.2M captions paired with 0.5M audio clips. We term it Large Language Model based Pseudo music caption dataset, shortly, LP-MusicCaps. We conduct a systemic evaluation of the large-scale music captioning dataset with various quantitative evaluation metrics used in the field of natural language processing as well as human evaluation. In addition, we trained a transformer-based music captioning model with the dataset and evaluated it under zero-shot and transfer-learning settings. The results demonstrate that our proposed approach outperforms the supervised baseline model.

AK

78,794 görüntüleme • 3 yıl önce

🎶 Nobody Festival 2025 wrapped up—AI music creation is entering a new era! 🔥 With AI + Web3 revolutionizing content creation, Fireverse was honored to be part of this festival, joining global investors, entertainment pioneers, and Web3 leaders to explore how AIGC is transforming the future of music! 🎼🚀 🎧 Festival Highlights: 🔹 AI-powered music creation unlocking personalized and immersive Web3 music experiences! 🔹 Industry experts discussing the limitless potential of AI in the music industry. 🔹 5,000 USDT community challenge igniting creativity and passion for music! Fireverse is pushing the boundaries of AI-driven music, empowering everyone to become a creator! Huge thanks to our partners for their support—we can't wait for the next gathering to shape the future of AI music together! 🔥 🔗 Relive the highlights 👉
1:25

🎶 Nobody Festival 2025 wrapped up—AI music creation is entering a new era! 🔥 With AI + Web3 revolutionizing content creation, Fireverse was honored to be part of this festival, joining global investors, entertainment pioneers, and Web3 leaders to explore how AIGC is transforming the future of music! 🎼🚀 🎧 Festival Highlights: 🔹 AI-powered music creation unlocking personalized and immersive Web3 music experiences! 🔹 Industry experts discussing the limitless potential of AI in the music industry. 🔹 5,000 USDT community challenge igniting creativity and passion for music! Fireverse is pushing the boundaries of AI-driven music, empowering everyone to become a creator! Huge thanks to our partners for their support—we can't wait for the next gathering to shape the future of AI music together! 🔥 🔗 Relive the highlights 👉

Fireverse Ventures

17,922 görüntüleme • 1 yıl önce

We didn’t believe in much, except for love. And through love, some of us came to believe in God. The most romantic song of our generation, from the man whose guitar made the music sing. “There is a light and it never goes out.”
0:35

We didn’t believe in much, except for love. And through love, some of us came to believe in God. The most romantic song of our generation, from the man whose guitar made the music sing. “There is a light and it never goes out.”

County Highway

14,561 görüntüleme • 9 ay önce

A few months ago, I started exploring AI, music, and creativity with my son. He started showing a passion for music, so we decided to create an experimental music project that fuses all our passions. A musical exploration that blended our love for Trap hip-hop, metal, and anime gave birth to "Afraid2Sl33p." Our first single, "Come Undone," will be released on streaming platforms as part of a self-titled 8-track EP in a few weeks. Here is our first AI music video. Music created using Suno V5, lyrics written by my son and me. Keep creating and keep exploring. Cheers.
2:25

A few months ago, I started exploring AI, music, and creativity with my son. He started showing a passion for music, so we decided to create an experimental music project that fuses all our passions. A musical exploration that blended our love for Trap hip-hop, metal, and anime gave birth to "Afraid2Sl33p." Our first single, "Come Undone," will be released on streaming platforms as part of a self-titled 8-track EP in a few weeks. Here is our first AI music video. Music created using Suno V5, lyrics written by my son and me. Keep creating and keep exploring. Cheers.

Dave Clark

162,033 görüntüleme • 8 ay önce

🚀 Introducing HunyuanVideo-Avatar, a model jointly developed by Tencent Hunyuan and Tencent Music, bringing photos to life. ✅ Upload a photo + audio — auto-detect scene context & emotion, then generate lifelike speech/singing with dynamic visuals. ✅ Supports multi-style, multi-species scenarios and excels in multi-character interactions. ✅ Built for short video creation, e-commerce, advertising, and more — already deployed in multiple apps across Tencent Music Entertainment Group. The single-character mode of HunyuanVideo-Avatar is now open-sourced and live on the Hunyuan website, supporting audio up to 14 seconds for video generation. The multi-character mode will be open-sourced soon. Try it on: Project Page: Github: Tech report: #Tencent #Hunyuan
1:01

🚀 Introducing HunyuanVideo-Avatar, a model jointly developed by Tencent Hunyuan and Tencent Music, bringing photos to life. ✅ Upload a photo + audio — auto-detect scene context & emotion, then generate lifelike speech/singing with dynamic visuals. ✅ Supports multi-style, multi-species scenarios and excels in multi-character interactions. ✅ Built for short video creation, e-commerce, advertising, and more — already deployed in multiple apps across Tencent Music Entertainment Group. The single-character mode of HunyuanVideo-Avatar is now open-sourced and live on the Hunyuan website, supporting audio up to 14 seconds for video generation. The multi-character mode will be open-sourced soon. Try it on: Project Page: Github: Tech report: #Tencent #Hunyuan

Tencent Hy

218,408 görüntüleme • 1 yıl önce