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。

We're releasing MuScriptor, the best open model for multi-instrument transcription to date, created in collaboration with Mirelo. Give it a recording in any genre: pop, classical, metal, jazz, whatever, and it transcribes the individual instruments into MIDI. Link in 🧵

kyutai

28,012 subscribers

307,852 次观看 • 3 个月前 •via X (Twitter)

科学技术音乐

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

your band's jam session, but now it's editable MIDI Muscriptor (Mirelo x Kyutai) is the first model that transcribes audio into per-instrument MIDI note tracks really well ▶️ on Spaces

your band's jam session, but now it's editable MIDI Muscriptor (Mirelo x Kyutai) is the first model that transcribes audio into per-instrument MIDI note tracks really well ▶️ on Spaces

Hugging Apps

21,206 次观看 • 2 个月前

Our audio-to-MIDI model, MuScriptor, now also detects tempo! You can directly drag-and-drop the MIDI into a DAW and it just works, without you having to tempo-match manually. Have fun!

Our audio-to-MIDI model, MuScriptor, now also detects tempo! You can directly drag-and-drop the MIDI into a DAW and it just works, without you having to tempo-match manually. Have fun!

kyutai

28,115 次观看 • 2 个月前

the biggest pop crime is katy perry & rihanna recording a song together in their prime and never releasing it

the biggest pop crime is katy perry & rihanna recording a song together in their prime and never releasing it

kanishk

27,424 次观看 • 3 个月前

MuScriptor, our music transcription model, can now make sheet music and tabs! We export PDFs and editable MusicXML. Under the hood, we generate these from MIDI using MuseScore Studio + some custom preprocessing.

MuScriptor, our music transcription model, can now make sheet music and tabs! We export PDFs and editable MusicXML. Under the hood, we generate these from MIDI using MuseScore Studio + some custom preprocessing.

kyutai

37,856 次观看 • 2 个月前

Created this mixed media video using the 'invideo editor', just by chatting with an editing agent. ~ Asked the agent to break up the original video into individual frames (for this one it was 12 fps) ~ Described the mixed media style we wanted in detail to the agent (you could also give the agent reference images and videos that you feel work best for the video you're creating), ~ And then asked it to generate each frame using an image-gen model and line it back up in the right place as a separate layer. Did all this in ~30 minutes.

Created this mixed media video using the 'invideo editor', just by chatting with an editing agent. ~ Asked the agent to break up the original video into individual frames (for this one it was 12 fps) ~ Described the mixed media style we wanted in detail to the agent (you could also give the agent reference images and videos that you feel work best for the video you're creating), ~ And then asked it to generate each frame using an image-gen model and line it back up in the right place as a separate layer. Did all this in ~30 minutes.

Invideo

219,869 次观看 • 1 个月前

$/／ 🎉 Talent-Created Create Chart Spotlight! \＼ Take a look at part of the chart for “Lioness’ Pride,” created by #ShishiroBotan in collaboration with the #holodori chart team 🏰🎶 Give it a try! ✨ #holodori$

/／ 🎉 Talent-Created Create Chart Spotlight! \＼ Take a look at part of the chart for “Lioness’ Pride,” created by #ShishiroBotan in collaboration with the #holodori chart team 🏰🎶 Give it a try! ✨ #holodori

hololive Dreams

72,781 次观看 • 1 个月前

🆓 Free Open-Source Jev 🤝 LangSmith Gateway Decision models are becoming a first-class part of the LangSmith Gateway! We're serving SemIf, an open-source decision model, free for the next week. Compatible with the TypeSafe SDK - just change a string to try it! Docs in 🧵

🆓 Free Open-Source Jev 🤝 LangSmith Gateway Decision models are becoming a first-class part of the LangSmith Gateway! We're serving SemIf, an open-source decision model, free for the next week. Compatible with the TypeSafe SDK - just change a string to try it! Docs in 🧵

Jacob Lee

40,499 次观看 • 1 个月前

Crimson Desert has the best Open-World in any game. It may not be the best open-world game but it tops in the sense of adventure it produces through it's open-world.

Crimson Desert has the best Open-World in any game. It may not be the best open-world game but it tops in the sense of adventure it produces through it's open-world.

SpawnYaard 🎮

14,572 次观看 • 6 个月前

The Gothic 1 Remake will feature a real Orc language, created in collaboration with an expert in linguistics. In the game, you’ll be able to learn it and speak to Orcs in both the human and Orc languages. Emma Gregory Adam Diggle

The Gothic 1 Remake will feature a real Orc language, created in collaboration with an expert in linguistics. In the game, you’ll be able to learn it and speak to Orcs in both the human and Orc languages. Emma Gregory Adam Diggle

Gothic Game

23,797 次观看 • 11 个月前

Running Python in Mistral AI Le Chat! Give it a try! Link in 🧵

Running Python in Mistral AI Le Chat! Give it a try! Link in 🧵

Mistral AI Developers

14,646 次观看 • 1 年前

For the first time we're witnessing a government that initiates a major project and completes it in time. Give it to Ruto. 🔥

For the first time we're witnessing a government that initiates a major project and completes it in time. Give it to Ruto. 🔥

Captain Kipkorir

31,692 次观看 • 4 个月前

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇

today, we're releasing an open version of Krea-1. FLUX Krea is a new SOTA open-source image model with incredible realism and aesthetics. try it for free 👇

Krea

1,055,965 次观看 • 1 年前

We're releasing OVIE, a novel view generation model trained entirely on single images. No multi-view datasets needed. Given a single image, it generates novel views of any scene in real time, running orders of magnitude faster than competing approaches.

We're releasing OVIE, a novel view generation model trained entirely on single images. No multi-view datasets needed. Given a single image, it generates novel views of any scene in real time, running orders of magnitude faster than competing approaches.

kyutai

31,449 次观看 • 6 个月前

Stop spending hours recording your videos 🤌 There's a new way to do it in 60 seconds. Without a camera... Now you can turn your any image into a high-quality talking video with VEED's new AI model, Fabric 1.0 Steal the tool in the first comment 👇 * I've been testing it secretly, and the results are a game-changer for scaling content creation

Stop spending hours recording your videos 🤌 There's a new way to do it in 60 seconds. Without a camera... Now you can turn your any image into a high-quality talking video with VEED's new AI model, Fabric 1.0 Steal the tool in the first comment 👇 * I've been testing it secretly, and the results are a game-changer for scaling content creation

AmirMušić

34,232 次观看 • 1 年前

Most beautiful destinations in the world, you may fall in love with the picturesque view of mother nature. Open the thread 🧵 and enjoy it A Thread 🧵 1. Kerala, India

Most beautiful destinations in the world, you may fall in love with the picturesque view of mother nature. Open the thread 🧵 and enjoy it A Thread 🧵 1. Kerala, India

Earth_Seeker

105,095 次观看 • 1 年前

grok bot can now make purchases for you! give it a card with stripe link, and let it buy whatever you need (btw grok bot created this video end to end)

grok bot can now make purchases for you! give it a card with stripe link, and let it buy whatever you need (btw grok bot created this video end to end)

eric zakariasson

40,620 次观看 • 2 个月前

🇺🇸 While everyone's wondering when human-like robots will take over the world, NVIDIA CEO Jensen Huang hinted that any industrial object you use in the future could be as intelligent as your colleague. "Every single instrument, whether it is ultrasound or CT, whatever instrument we interact with in a hospital, will be agentic. That instrument will be interacting with patients and doctors in very unique ways." Source: The All-In Podcast

🇺🇸 While everyone's wondering when human-like robots will take over the world, NVIDIA CEO Jensen Huang hinted that any industrial object you use in the future could be as intelligent as your colleague. "Every single instrument, whether it is ultrasound or CT, whatever instrument we interact with in a hospital, will be agentic. That instrument will be interacting with patients and doctors in very unique ways." Source: The All-In Podcast

Mario Nawfal

29,412 次观看 • 7 个月前

One of the best formats for promoting your app for organic and ads👇 A talking person in the corner + a screen recording of your app It works because it feels personal while showing the product in action, which helps drive conversions Best part? It works for any app and you can either record yourself or use an AI avatar like I did here with Arcads

César Álvarez

19,101 次观看 • 4 个月前

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity Computer is massively multi-model. Computer orchestrates models to run agents in parallel, leveraging Opus to match each task to the model best suited for it. In total, Computer can route work across 19 different models.

Perplexity

534,569 次观看 • 8 个月前

Seedance 2.5 - Prompt Share ✨ This prompt turns any character into a dance video, creating choreography that matches the character’s style and personality. I tried it with my character, and it should work with any character. Prompt in thread 🧵

Seedance 2.5 - Prompt Share ✨ This prompt turns any character into a dance video, creating choreography that matches the character’s style and personality. I tried it with my character, and it should work with any character. Prompt in thread 🧵

Kiki

50,198 次观看 • 1 个月前