Jordi Pons @jordiponsdotme
Music, audio, and deep learning research at @StabilityAI ~ Building bridges between audio signal processing wisdom and deep learning ~ Prev: @Dolby & @MTG_upf. jordipons.me Barcelona Joined February 2017-
Tweets1K
-
Followers4K
-
Following731
-
Likes5K
SAM + Optical Flow = FlowSAM FlowSAM can discover and segment moving objects in a video and outperforms all previous approaches by a considerable margin in both single and multi-object benchmarks 🔥 robots.ox.ac.uk/~vgg/research/…
The @stableaudio team has released their research paper detailing the technology behind Stable Audio 2.0🎵
The @stableaudio team has released their research paper detailing the technology behind Stable Audio 2.0🎵
Excited to share my first track entitled "End Days" created using @udiomusic. The music video was created with @neuralframes using a custom model generated with images created with @midjourney. Inspired by "The Scream", i tried to bring the out the style while injecting my own…
i have a feeling we need a lawsuit or something
i have a feeling we need a lawsuit or something https://t.co/UerDzOOxhi
Our very own @AlfieBradic morphing guitar with our metal vocals model!
Long-form music generation with latent diffusion. arxiv.org/abs/2404.10301
Long-form music generation with latent diffusion Audio-based generative models for music have seen great strides recently, but so far have not managed to produce full-length music tracks with coherent musical structure. We show that by training a generative model on long
My favourite part of our paper: the QR codes section.
My favourite part of our paper: the QR codes section. https://t.co/GnoUHDHt0e
The Stable Audio 2.0 paper is out! Highlights: - 1.1B parameter diffusion transformer - Outputs up to 4 minutes 45 seconds - New 2048x downsampled VAE
The Stable Audio 2.0 paper is out! Highlights: - 1.1B parameter diffusion transformer - Outputs up to 4 minutes 45 seconds - New 2048x downsampled VAE
Announcing Stable Audio 2.0 paper! - DiT beats U-net - Autoencoder compression ftw - Achieved 4:45 long window (better at song structure than LMs) - is fast
Announcing Stable Audio 2.0 paper! - DiT beats U-net - Autoencoder compression ftw - Achieved 4:45 long window (better at song structure than LMs) - is fast
``Long-form music generation with latent diffusion,'' Zach Evans, Julian D. Parker, CJ Carr, Zack Zukowski, Josiah Taylor, Jordi Pons, ift.tt/Xdl39hq
We've released our paper on the model behind Stable Audio 2.0! Our model can generate high-fidelity music with lengths up to 4 minutes 45 seconds. Paper: arxiv.org/abs/2404.10301 Demos: stability-ai.github.io/stable-audio-2… SoundCloud: soundcloud.com/stable-audio/s… youtube.com/watch?v=UpxIGa…
4 minutes 45 sec long model. Can listen our SoundCloud playlist or YouTube radio while reading the paper :) 🎧 SoundCloud: soundcloud.com/stable-audio/s… 📻 YouTube stream: youtube.com/live/yvOXZ6SV2…
4 minutes 45 sec long model. Can listen our SoundCloud playlist or YouTube radio while reading the paper :) 🎧 SoundCloud: soundcloud.com/stable-audio/s… 📻 YouTube stream: youtube.com/live/yvOXZ6SV2…
🎶🎸🥁🎼👨🎤🎶🎹🎵🎛️🎷🎺🎻🎙️
🎵The Stable Audio 2.0 user guide is here 🎵 Here’s some tips and tricks to get the most out of the 2.0 model. You can access the full guide here: stableaudio.com/user-guide (1/5)
Stable LM 2 12B is a pair of powerful 12 billion parameter language models trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch, featuring a base and instruction-tuned model. You can now try the model here: huggingface.co/stabilityai/st……
We caught up with the legendary @PetarV_93 to discuss TacticAI, which he developed with his colleagues at @GoogleDeepMind in collaboration with @LFC club!
ODDs, the best prompter I know, described very well the essence of @stableaudio as an INSTRUMENT. “It’s more an instrument, than instant gratification” “Use prompts as a way to access your creativity”
ODDs, the best prompter I know, described very well the essence of @stableaudio as an INSTRUMENT. “It’s more an instrument, than instant gratification” “Use prompts as a way to access your creativity”
AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxChristian Steinmetz @csteinmetz1
5K Followers 2K Following AI for audio • PhD Student @c4dm MSc @mtg_upf • Previously Intern @Adobe @Meta @DolbyKeunwoo Choi @keunwoochoi
6K Followers 800 Following AI x {LLM Engineer @PrescientDesign @genentech, Advisor @gaudiolab}. music, audio, language, AI. Prev: @BytedanceTalk, @spotify, @c4dm @qmul.Oriol Nieto @urinieto
2K Followers 1K Following Researcher at Adobe Research. Machine learning on audio. General Co-Chair of ISMIR24. Screamer. Oaklander born in Barcelona. Titan. He/they 🏳🌈Pedro Sarmento @umpedronosapato
2K Followers 2K Following PhD researcher in AI & Music @CDT_AI_Music @c4dm @QMUL a bit more at https://t.co/Ame4OSwQjqdadabots @dadabots
9K Followers 7K Following Jupyter notebook prompt jockeys. Eliminating humans from music. AI Death Metal. 🧠 Research @Harmonai_org 🔥🦇🔉@NoiseDAO Artist @artblocks_io @braindrops_artIlaria Manco @Ilaria__Manco
2K Followers 936 Following PhD student @c4dm, working on multimodal learning for music understanding • Former intern @GoogleDeepMind @AdobeResearch @Sony • DJISMIR Conference @ISMIRConf
3K Followers 194 Following The 25th International Society for Music Information Retrieval Conference, Nov 10-14, 2024. 🎶 Save The Date: Nov 10-14th, 2024 in San Francisco, USA #ISMIR2024Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).Ben Hayes @benhayesmusic
2K Followers 1K Following PhD student in machine learning for audio synthesis at @c4dm. former research intern @sonycslparis and @bytedance.Chris Donahue @chrisdonahuey
5K Followers 1K Following Generative models, musical expression for all. Assistant professor at CMU CSD. Part time research at Google Magenta (views my own)Titouan Parcollet @ParcolletT
3K Followers 404 Following Research Scientist @samsung. Affiliated Lecturer @Cambridge_Uni | @CaMLSys. Associate Professor on leave @UnivAvignon. Co-creator of @SpeechBrain1.Joan Serrà @serrjoa
2K Followers 598 Following Machine learning @SonyAI_global. Focus on #audio & #multimedia synthesis/analysis/retrieval. Personal account.Delip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈Desh Raj @rdesh26
3K Followers 2K Following Research Scientist @Meta (AI Speech) | Previously: @jhuclsp, @IITGuwahatiJonathan Le Roux @JonathanLeRoux
1K Followers 314 Following Speech and audio research scientist at MERL. Opinions never really my own.Marco Martínez @marcoamaram
912 Followers 325 Following music technology researcher @Sony interned at @AdobeResearch phd @c4dm @qmul music production https://t.co/hC8uy7qfBzEthan Manilow @ethanmanilow
2K Followers 582 Following i think about music & ml a lot. Research Scientist @GoogleDeepMind @GoogleMagenta. phd from the interactive audio lab @northwesternU. prev @merl_news. he/himVivek Kumar @vivek_kumar
2K Followers 614 Following Senior Manager, Sound Understanding at @googleai. Ex @Dolby & @Broadcom. Talks and Investments 👉🏽 https://t.co/Iqmk4l7YMF저시연 @jeosiyeon14755
9 Followers 2K Followinganimeidol @metaanimeidol
22 Followers 325 FollowingCiprian Cîmpan @devnulli
365 Followers 2K Following I build your next-gen products in my resilient AI cloud @fifi_ai 🤖 Full-stack engineer obsessed with DevOps 🚀Zongcheng Wang @zcwang1222
5 Followers 275 Following¯\_(ツ)_/¯asaurus .. @jameshurlbut
602 Followers 3K Following 3D Gfx, art, music, surfing. Prototyping at Adobe SystemsPensé FFun @inftyCategory
113 Followers 6K Following정재민 @jjm50625811
0 Followers 10 FollowingZhaoyang Wang @wangwan83764204
301 Followers 4K Following CS PhD student at UoB in the United Kingdom. Research interests: Automated Machine Learning, Online Learning, and Reinforcement Learning 🏳️🌈Léa Briand @lea_ibrd
95 Followers 195 Following Data Scientist at @Deezer - Music Recommendation From @ENSAEParisTech • @UPMC @Sorbonne_Univ_ - @master_dacEleonora Lopez @elelopess
34 Followers 80 FollowingHan Park @ipuris
317 Followers 1K Following Majoring in network security and authentication. Co-founder and CTO of @deeplyinc. :DAlain Riou @howariou
105 Followers 172 Following PhD student @ Sony CSL × Télécom Paris Very interested in AI, music and AI for musicijohn @john_whickins
219 Followers 2K Following Lost in the sea of life, making waves with AI. #AIenthusiast #lostbutnotfoundRiccardo Fosco Gramac.. @riccardofosco
45 Followers 95 Following PhD Student in AI for Audiovisual Media @IspammL, @SapienzaRoma | Visiting Academic @c4dm, @QMULhertzfelt.io @hertzfelt_io
146 Followers 541 Following AE alum @FullSail 🎛 | Writing code, #AI augmented audio, developer and multidisciplinary creative. ♒️ #AudioOps, 🧠#AIOps 💬#LLMops, 🦾#GenAI #MLOps.Amantur Amatov @ama_mato
17 Followers 39 FollowingJames Moore @jamesdmoore614
1K Followers 962 Following DON'T PANIC BCI - Neurofeedback - VR - Biofeedbackgaracybe @garacybe
102 Followers 2K Followingmeng shao @shao__meng
2K Followers 1K Following Developer | Exploring Gen AI 👨💻 Passionate about LLM and T2I 🧠 Share images generated by 👇🏻 Freepik, Ideogram, Stylar and othersScott Haynes @scotthaynesAi
7K Followers 7K Following Creative AI | Artist | Crypto | Community /🤝🐿️ @neuralframes. Dm to book a callNymph 🏳️⚧�.. @RhizoNymph
6K Followers 2K Following Rhizomatic cartographer and technomancer obsessed with many facets of reality. Hip hop/hyperpop enthusiast. Musician and creator. Engineer @SearchOnDora.Jayeon Yi @jayeon_yi
53 Followers 89 Following M.S. student @UMichECE / (Music, Audio, Speech) × AI × Real-time. Previously with MARG (Music and Audio Research Group) @SeoulNatlUniReinhard Kepplinger @RKepplinger3d
18 Followers 176 FollowingBobber Cheng @bobbercheng
17 Followers 1K FollowingWill @Will_Iam_W
87 Followers 144 FollowingYuki Saito @ysaito_human
447 Followers 380 Following Lecturer (speech synthesis) @ The University of Tokyo, JapanWaseem Randhawa @mwaseemrandhawa
162 Followers 1K Following #PHD #TECIP #Rsearcher @ScuolaSantAnna @SantAnnaPisaliang wen @liang001_wen
57 Followers 786 FollowingPaul Singh @paul66430
0 Followers 3 FollowingRoyalCities @RoyalCities
29 Followers 137 Following Here to make some tunes and youtube documentariesLynn Cole 🏳️�.. @PriestessOfDada
3K Followers 5K Following I'm the High Priestess of Dada. Renegade process artist that specializes in singergens, character builders, diffusion models. No pencils only zuul She/herMusic Distro Labs @musicdistrolabs
17 Followers 43 Following Distribute your AI-generated music globally to Spotify, Apple Music, and more. Keep 90% of royalties. Completely free. Always.Donalyn Lee @DonalynLee9914
114 Followers 329 FollowingVenshiKibes @VenshiKibes
209 Followers 157 Following Under heaven, one can know clown world as clown world only because there is honking.Tony Hansmann @997unix
728 Followers 1K Following Work relentlessly to establish ground-state truth.Mitja Martini @MitjaMartini
30 Followers 88 Following On software development and operations in the cloud, #Python, #Excel #ChatGPT and other #llm.Christian Steinmetz @csteinmetz1
5K Followers 2K Following AI for audio • PhD Student @c4dm MSc @mtg_upf • Previously Intern @Adobe @Meta @DolbyKeunwoo Choi @keunwoochoi
6K Followers 800 Following AI x {LLM Engineer @PrescientDesign @genentech, Advisor @gaudiolab}. music, audio, language, AI. Prev: @BytedanceTalk, @spotify, @c4dm @qmul.Oriol Nieto @urinieto
2K Followers 1K Following Researcher at Adobe Research. Machine learning on audio. General Co-Chair of ISMIR24. Screamer. Oaklander born in Barcelona. Titan. He/they 🏳🌈Pedro Sarmento @umpedronosapato
2K Followers 2K Following PhD researcher in AI & Music @CDT_AI_Music @c4dm @QMUL a bit more at https://t.co/Ame4OSwQjqdadabots @dadabots
9K Followers 7K Following Jupyter notebook prompt jockeys. Eliminating humans from music. AI Death Metal. 🧠 Research @Harmonai_org 🔥🦇🔉@NoiseDAO Artist @artblocks_io @braindrops_artIlaria Manco @Ilaria__Manco
2K Followers 936 Following PhD student @c4dm, working on multimodal learning for music understanding • Former intern @GoogleDeepMind @AdobeResearch @Sony • DJISMIR Conference @ISMIRConf
3K Followers 194 Following The 25th International Society for Music Information Retrieval Conference, Nov 10-14, 2024. 🎶 Save The Date: Nov 10-14th, 2024 in San Francisco, USA #ISMIR2024Sander Dieleman @sedielem
50K Followers 2K Following Research Scientist at Google DeepMind. I tweet about deep learning (research + software), music, generative models (personal account).Ben Hayes @benhayesmusic
2K Followers 1K Following PhD student in machine learning for audio synthesis at @c4dm. former research intern @sonycslparis and @bytedance.Chris Donahue @chrisdonahuey
5K Followers 1K Following Generative models, musical expression for all. Assistant professor at CMU CSD. Part time research at Google Magenta (views my own)Stability AI @StabilityAI
189K Followers 31 Following We are building the foundation to activate humanity's potential.Titouan Parcollet @ParcolletT
3K Followers 404 Following Research Scientist @samsung. Affiliated Lecturer @Cambridge_Uni | @CaMLSys. Associate Professor on leave @UnivAvignon. Co-creator of @SpeechBrain1.Heiga Zen (全 炳河.. @heiga_zen
7K Followers 197 Following Principal Scientist (Director) @GoogleDeepMind in Japan. 波瀬小⇒一志中⇒鈴鹿高専⇒名工大 (IBM TJ Watson intern for a year)⇒東芝欧州研⇒Google (Speech🇬🇧⇒Brain🇯🇵) ⇒Google DeepMindJoan Serrà @serrjoa
2K Followers 598 Following Machine learning @SonyAI_global. Focus on #audio & #multimedia synthesis/analysis/retrieval. Personal account.Soumith Chintala @soumithchintala
186K Followers 877 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.Jonathan Le Roux @JonathanLeRoux
1K Followers 314 Following Speech and audio research scientist at MERL. Opinions never really my own.Marco Martínez @marcoamaram
912 Followers 325 Following music technology researcher @Sony interned at @AdobeResearch phd @c4dm @qmul music production https://t.co/hC8uy7qfBzJürgen Schmidhuber @SchmidhuberAI
107K Followers 0 Following Invented principles of meta-learning (1987), GANs (1990), Transformers (1991), very deep learning (1991), etc. Our AI is used many billions of times every day.Annamaria Mesaros @AnnamariaMsros
193 Followers 64 Following Associate Professor, Tampere University, FinlandEleonora Lopez @elelopess
34 Followers 80 FollowingHan Park @ipuris
317 Followers 1K Following Majoring in network security and authentication. Co-founder and CTO of @deeplyinc. :DLéa Briand @lea_ibrd
95 Followers 195 Following Data Scientist at @Deezer - Music Recommendation From @ENSAEParisTech • @UPMC @Sorbonne_Univ_ - @master_dacKovas Boguta 🫡 @kovasb
3K Followers 941 Following ML @midjourney. Ex-Twitter Cortex Applied Research, ex-Weebly, YC W2010 founder, ex-Wolfram.James Moore @jamesdmoore614
1K Followers 962 Following DON'T PANIC BCI - Neurofeedback - VR - Biofeedbackgandamu @gandamu_ml
16K Followers 5K Following Prev https://t.co/a96FYiLT41 · https://t.co/ren7Ov9vxx. Music videos: https://t.co/iFubkxDg5gRoyalCities @RoyalCities
29 Followers 137 Following Here to make some tunes and youtube documentariesLynn Cole 🏳️�.. @PriestessOfDada
3K Followers 5K Following I'm the High Priestess of Dada. Renegade process artist that specializes in singergens, character builders, diffusion models. No pencils only zuul She/herAndrew Sanchez @avincentsanchez
312 Followers 142 Following COO and Co-Founder at @udiomusic | Oxford DPhil | HarvardDavid Ding @DavidDingAI
2K Followers 121 Following CEO and co-founder of @udiomusic. ex Google DeepMindYaroslav Ganin @yaroslav_ganin
4K Followers 230 Following Co-Founder @udiomusic. Research Scientist. Previously: @DeepMindAI, Mila (Montréal, Canada), Skoltech (Moscow, Russia). Views are my own.Petar Veličković @PetarV_93
30K Followers 555 Following Staff Research Scientist @GoogleDeepMind | Affiliated Lecturer @Cambridge_Uni | Associate @clarehall_cam | GDL Scholar @ELLISforEurope. Monoids. 🇷🇸🇲🇪🇧🇦Mitja Martini @MitjaMartini
30 Followers 88 Following On software development and operations in the cloud, #Python, #Excel #ChatGPT and other #llm.AstroZeus⚡🧑�.. @zeus_astronaut
124 Followers 171 Following Ancap | – e/acc enthusiast | Melophile | Professor Sociolinguist, Discourse analyst & Techno-oracle.Destitech @destitech_com
22 Followers 46 Following Mener à destination vos projets technologiques, sans détour ni fausse route.Lightning_Shade @LightningShade0
315 Followers 362 Following I say what I think. Politically wrong-wing. Ask not what art can do for the world, ask what art can do for you. X (former employee), Y (current), Z (future)DerRichtige @richtige_der
684 Followers 537 Following strong beliefs loosely held. not good with emotional people, aka perfekt 𝕏 user🤦♂️VenshiKibes @VenshiKibes
209 Followers 157 Following Under heaven, one can know clown world as clown world only because there is honking.Nicholas Chase @Nicholasjackc
158 Followers 976 Followingburak cem @cemsayilar
86 Followers 283 Following data ml dl vm dm fm am pm | engineer @peakUpS | ituDekHarper.eth @DekHarper
3K Followers 5K Following New peer consultancy service launched, checkout link. Board Member @theFoodLife__Casey James Basichis @caseybasichis
493 Followers 273 Following Composer of Adventure Time, artist, film maker; the works...mohamed mez @mohamed17381489
34 Followers 1K FollowingPeter Varshavsky @pvarsh
63 Followers 138 Following Software eng at Stability AI. Former hobbies include statistics, music business, YouTubing.Guillaume Simiand @gsimiand
218 Followers 290 Following Humanités numériques, IA & génération de texte, aventure et aventuriers du XVIIIe siècle et d'ailleurs.Tony Hansmann @997unix
728 Followers 1K Following Work relentlessly to establish ground-state truth.Vitorio Vici @vitoriovici
61 Followers 154 FollowingVIPUL 👾 @VIPULGFX
302 Followers 113 FollowingPierreBezuchov01 @PBezuchov01
260 Followers 1K FollowingPinkal Vansia @Pinkal_vansia
41 Followers 48 FollowingAngelo D'Ambrosio �.. @Bakaburg1
1K Followers 2K Following MD, Public Health Specialist, ARHAI Expert at @ECDC_EU. #Computational #Epidemiology #InfectiousDiseases #DataScience. #Science addicted! #OneWorld🌍hfk @hafiskadyrow
109 Followers 169 FollowingJuraj Bednar @jurbed
10K Followers 1K Following 📖: Cryptocurrencies - Hack your way to a better life. Liberty / Entrepreneurship (@hacktrophy,@paralelnapolis).Hackyourself.io. Nostr: [email protected]thinkingbets @thinkingbets
192 Followers 567 Following ml | quant | crypto systematic asymmetry hunterAdnan Ahmad @BEAST_OFFICIIAL
113 Followers 677 FollowingNishant Nikhil @nishnik
847 Followers 859 Following Text to Speech @play_ht | previously 'idhar udhar dekh kar, baalo pe haath fer kar' founded https://t.co/4WsLeE45X6 | Ex-Amazon ML Applied ScientistAlways nice to see your research being used in real-world applications that people can enjoy! cosine.club uses our metric learning models trained on @discogs metadata to predict electronic music similarity and create playlists🎶💿
A new online digging tool recommends users electronic music tracks based on similarity. Read the news ra.co/news/80607
New paper from our team for the #icassp2024 Workshop on Explainable AI for Speech and Audio.
Excited to present our paper on interpretable music classification at #icassp2024's XAI-SA workshop in Seoul this Monday, April 15th (2nd oral session, 14:00 KST)! 📝pre-print: arxiv.org/abs/2402.09318 🔈examples: palonso.github.io/pecmae 💻code: github.com/palonso/pecmae [1/6]🧵👇
Thrilled to have attended #ICASSP24 in Seoul! 🇰🇷 The experience was great — met so many brilliant new people and caught up with old friends!
Today I presented an updated version of my overview talk on deep generative modelling at @IRI_robotics. Do you have any tips to prepare the next iteration ? sites.google.com/view/deep-lear…
After sharing some interesting results and inspiring presentations ☕️ it is time for a break and 📷 a group photo with the supervisors and the doctoral candidates TRAIL Midterm Meeting #TransparentInterpretableRobots
Songs in 6/8 are good by default, you have to work to make them bad.
Honored to see Mapache here 😜
New post is out! 🇰🇷 ICASSP 2024, eleven picks. jordipons.me/icassp-2024/
@StabilityAI @stableaudio The quality and acoustics are superb, well done. 👏
The @stableaudio team has released their research paper detailing the technology behind Stable Audio 2.0🎵
We've released our paper on the model behind Stable Audio 2.0! Our model can generate high-fidelity music with lengths up to 4 minutes 45 seconds. Paper: arxiv.org/abs/2404.10301 Demos: stability-ai.github.io/stable-audio-2… SoundCloud: soundcloud.com/stable-audio/s… youtube.com/watch?v=UpxIGa…
If you wish to familiarize yourself with recent strong models for sound separation, look into our jounals @TismirJ that just came out this week Those are reports on the Sound Demixing Challenge 2023 where I served as the general chair Music Track: transactions.ismir.net/articles/10.53……
We are happy to announce that our two papers summarizing the Sound Demixing Challenge 2023 have been published in @TismirJ ! Thank you to everyone for their hard work! Music Track: transactions.ismir.net/articles/10.53… Cinematic Track: transactions.ismir.net/articles/10.53…
So grateful to see SyncFusion on this list, together with other fantastic works! @IspammL
New post is out! 🇰🇷 ICASSP 2024, eleven picks. jordipons.me/icassp-2024/
Great to see SyncFusion in this list. There’s so much work to do in controllable video-to-audio synthesis.
New post is out! 🇰🇷 ICASSP 2024, eleven picks. jordipons.me/icassp-2024/
😉😊
New post is out! 🇰🇷 ICASSP 2024, eleven picks. jordipons.me/icassp-2024/
This tweet nerdsniped me into making this, needs some work but its functional. github.com/RhizoNymph/ssm…
iiia.csic.es/media/filer_pu… if you want to know how they made those, they're actually a really cool way to visualize song structure what
Musicians, level up your prompting skills. Josiah Taylor of @StabilityAI @harmonai_org will lead a collaborative prompting session at Sónar+D. sonar.es/en/activity/ta… Tardes de Prompting - Music and Audio | presented by Stability AI | Friday 14th June #sonarplusd #sonar2024
使用 latent diffusion 生成长篇音乐 🎵🎵🎵 来自 Stability AI Harmonai 🎵 该模型采用了一个在高度下采样的连续潜在表示上运行的扩散变换器,可以生成最长为 4m 45s 的音乐,同时实现与原音频相同的结构和质量。 🎵 该模型在音频质量和文本提示对齐方面的生成实现了最先进的性能,并且能够在 13s…
We've released our paper on the model behind Stable Audio 2.0! Our model can generate high-fidelity music with lengths up to 4 minutes 45 seconds. Paper: arxiv.org/abs/2404.10301 Demos: stability-ai.github.io/stable-audio-2… SoundCloud: soundcloud.com/stable-audio/s… youtube.com/watch?v=UpxIGa…
When an old work gets momentarily revived 😁 dx.doi.org/10.1109/TMM.20… I remember we won the MIREX Structure Annotation task with that (if someone remembers what that was), back in 2012, and stayed SOTA for some time (nowadays you stay SOTA for what, 20 mins?).
Excited to share my first track entitled "End Days" created using @udiomusic. The music video was created with @neuralframes using a custom model generated with images created with @midjourney. Inspired by "The Scream", i tried to bring the out the style while injecting my own…