正在加载视频...

视频加载失败

返回首页

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really...

multimodalart's profile picture

apolinario (poli)

15,803 subscribers

41,484 次观看 • 1 个月前 •via X (Twitter)

艺术音乐科学技术
LIVE

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

🥳 Announcing Stable Audio 3 🍕 🏆 fastest music models ever 💻 runs on MacBookPro M-series 🧪 break it plz 🧠 LoRA finetune in < 1h 📷 Sm = faster, Medium = qualityer ⚡ 59x realtime on M5 Pro One-liner fast install: curl -LsSf | bash
0:17

🥳 Announcing Stable Audio 3 🍕 🏆 fastest music models ever 💻 runs on MacBookPro M-series 🧪 break it plz 🧠 LoRA finetune in < 1h 📷 Sm = faster, Medium = qualityer ⚡ 59x realtime on M5 Pro One-liner fast install: curl -LsSf | bash

dadabots

58,244 次观看 • 1 个月前

Stable Audio 3.0 is now Day-0 supported in ComfyUI. Open-weight music models (fully licensed data)—from quick SFX and short tracks to longer, more musical pieces—inside the workflows you already use.
0:17

Stable Audio 3.0 is now Day-0 supported in ComfyUI. Open-weight music models (fully licensed data)—from quick SFX and short tracks to longer, more musical pieces—inside the workflows you already use.

ComfyUI

209,395 次观看 • 1 个月前

ถ้าไม่มีเสียงพิธีกร ก็นึกว่าเปิด audio คนถึงไม่ค่อยเชื่อว่าร้องสดกัน เพราะร้องละเหมือนเปิดซีดีอ่า 555555555 stable เกิ๊น
0:17

ถ้าไม่มีเสียงพิธีกร ก็นึกว่าเปิด audio คนถึงไม่ค่อยเชื่อว่าร้องสดกัน เพราะร้องละเหมือนเปิดซีดีอ่า 555555555 stable เกิ๊น

𝙎𝙪𝙘𝙝𝙣𝙚𝙨𝙨.555

146,098 次观看 • 2 年前

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, on-the-go creation, it turns your next quick idea into up to 11 seconds of audio. Generate drum loops, foley, riffs, and textures right where you are. No cords 🔌 just chords 🎹 You can learn more here:
0:17

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, on-the-go creation, it turns your next quick idea into up to 11 seconds of audio. Generate drum loops, foley, riffs, and textures right where you are. No cords 🔌 just chords 🎹 You can learn more here:

Stability AI

94,796 次观看 • 1 年前

Seedance 1.5 just dropped. Is it a Veo killer? It also comes with native audio and lip sync. The first tests I made look amazing so far. The audio is really clean and the video quality is fantastic. If you’re curious, the Veo 3 examples are in the comments
0:18

Seedance 1.5 just dropped. Is it a Veo killer? It also comes with native audio and lip sync. The first tests I made look amazing so far. The audio is really clean and the video quality is fantastic. If you’re curious, the Veo 3 examples are in the comments

Halim Alrasihi

42,805 次观看 • 6 个月前

Kling 2.6 Voice Control just fixed the biggest pain point in audio generation: stable character voices.
0:18

Kling 2.6 Voice Control just fixed the biggest pain point in audio generation: stable character voices.

SARAH

1,114,990 次观看 • 6 个月前

Android Release Timeline for Pixel Phones: Beta and Stable Dates 1. Android 16 QPR1 (Stable) - Sep 3, 2025 (Expected) 2. Android 16 QPR2 (Stable) - Dec, 2025 3. Android 17 (Dev Preview) - Nov, 2025 (Expected) 4. Android 17 (Stable) - June, 2026 (Expected) #Android #GooglePixel
0:11

Android Release Timeline for Pixel Phones: Beta and Stable Dates 1. Android 16 QPR1 (Stable) - Sep 3, 2025 (Expected) 2. Android 16 QPR2 (Stable) - Dec, 2025 3. Android 17 (Dev Preview) - Nov, 2025 (Expected) 4. Android 17 (Stable) - June, 2026 (Expected) #Android #GooglePixel

Pixel UI by Google

34,524 次观看 • 10 个月前

Tencent just open-sourced HunyuanVideo-Foley: a model that generates sound effects directly from video One step closer to open models with native audio like Veo 3!
0:10

Tencent just open-sourced HunyuanVideo-Foley: a model that generates sound effects directly from video One step closer to open models with native audio like Veo 3!

Miguel | AP

21,961 次观看 • 10 个月前

Why was Bay 3 already wide open before Karen Read’s vehicle even entered the sallyport? We’ve all heard the audio of Berkowitz asking Officer Theodore to close bays 3 and 4 but here’s the problem Where’s the call to open them in the first place? And where’s the video showing those doors actually being opened and closed? It’s a simple question of chain of custody for the audio logs: if the door was operated, it should leave an audio footprint. Something here is incomplete.
0:14

Why was Bay 3 already wide open before Karen Read’s vehicle even entered the sallyport? We’ve all heard the audio of Berkowitz asking Officer Theodore to close bays 3 and 4 but here’s the problem Where’s the call to open them in the first place? And where’s the video showing those doors actually being opened and closed? It’s a simple question of chain of custody for the audio logs: if the door was operated, it should leave an audio footprint. Something here is incomplete.

Dixie Normus

22,901 次观看 • 8 个月前

You can now use Flux and other image generation models for free on PUBLC, including: - Flux.1 Schnell & Flux.1 Dev by Black Forest Labs - Stable Diffusion 3 by Stability AI - SDXL-Lightning-4Step by ByteDance Unleash your creativity✨ Try it now -
0:14

You can now use Flux and other image generation models for free on PUBLC, including: - Flux.1 Schnell & Flux.1 Dev by Black Forest Labs - Stable Diffusion 3 by Stability AI - SDXL-Lightning-4Step by ByteDance Unleash your creativity✨ Try it now -

PUBLC

648,867 次观看 • 1 年前

Moaning audio :3
0:16

Moaning audio :3

baguette

45,336 次观看 • 2 年前

Stable Public Testnet is now live. A new era of payments begins. Stable offers a USDT-native environment built for fast, predictable, and frictionless transactions Developers can now deploy, test, and interact with the Stablechain. Start Building:
0:10

Stable Public Testnet is now live. A new era of payments begins. Stable offers a USDT-native environment built for fast, predictable, and frictionless transactions Developers can now deploy, test, and interact with the Stablechain. Start Building:

Stable

213,365 次观看 • 8 个月前

🚨 BREAKING: The fastest AI voice model just dropped! Cartesia Sonic-2 delivers real-time voice AI with 40ms latency—twice as fast as anything out there. And with instant voice cloning (only 3 seconds of audio needed), emotion control, and audio infilling, voice AI will never be the same. Here's what you need to know👇
0:10

🚨 BREAKING: The fastest AI voice model just dropped! Cartesia Sonic-2 delivers real-time voice AI with 40ms latency—twice as fast as anything out there. And with instant voice cloning (only 3 seconds of audio needed), emotion control, and audio infilling, voice AI will never be the same. Here's what you need to know👇

SARAH

530,539 次观看 • 1 年前

make sure ur audio is turned down :3
0:17

make sure ur audio is turned down :3

mennah :3

195,403 次观看 • 6 个月前

🗣There is your couple events surprises abroad? F:This year not sure B:yes F:we two just open new companies We ask for B:it's stable first F:yes make it really stable FB SONGKRAN WITH CTW #CTWSongkran26xFreenBecky #FreenBecky #ฟรีนเบค
0:19

🗣There is your couple events surprises abroad? F:This year not sure B:yes F:we two just open new companies We ask for B:it's stable first F:yes make it really stable FB SONGKRAN WITH CTW #CTWSongkran26xFreenBecky #FreenBecky #ฟรีนเบค

Love Dino Ji 공룡 사랑~

88,541 次观看 • 3 个月前

Hindi Speech Model should be free and open-source. And we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!
0:11

Hindi Speech Model should be free and open-source. And we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!

Dheemanth Reddy

59,602 次观看 • 1 年前

🚨WALKOFF ALERT🚨 Chase Wilcox doubles to left center field and No.3 Roll Stable wins it in extras and takes the series! #D2Baseball
0:19

🚨WALKOFF ALERT🚨 Chase Wilcox doubles to left center field and No.3 Roll Stable wins it in extras and takes the series! #D2Baseball

D2 Baseball

14,338 次观看 • 1 年前

CW: Vore, Audio Added audio to a gif I found that I really liked :3 🎨: Retrobelly on DA (idk if they have something on this platform) #vore #animation #audio
0:10

CW: Vore, Audio Added audio to a gif I found that I really liked :3 🎨: Retrobelly on DA (idk if they have something on this platform) #vore #animation #audio

🐰Marshy🐰 🔞 (1/3)

15,552 次观看 • 3 个月前