Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Using Stable Audio 3 to generate variations of an existing loop. Unconditional generation (no prompt), renoising the latents to 0.5, and just using different seeds seems to generate a nice neighbourhood around the original. Generally keeps the harmonic context and feel.

Tero Parviainen

9,828 subscribers

10,890 Aufrufe • vor 4 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

16 Kommentare

Profilbild von Yinbo Wang

Yinbo Wangvor 4 Monaten

Cool! Additionally, with Stable Audio 3, its fast inference speed feels like it could enable some very interesting possibilities in live music.

Profilbild von Tero Parviainen

Tero Parviainenvor 4 Monaten

Yeah! Small models usable on device in real time, big unlock

Profilbild von Oliver Camp

Oliver Campvor 4 Monaten

crazy

Profilbild von Rock Mafia

Rock Mafiavor 4 Monaten

Impressive.

Profilbild von ZE Records

ZE Recordsvor 4 Monaten

Any links to project?

Profilbild von Tero Parviainen

Tero Parviainenvor 4 Monaten

alas not to my specific setup, but all the interesting stuff is done by the stable audio 3 medium model

Profilbild von Ulterior 🏔️

Ulterior 🏔️vor 4 Monaten

I wonder how well it will work for time-stretching. This is the most painful point in my sampling flow currently, old tracks just cannot be stretched into the grid with the common algorithms

Profilbild von Tero Parviainen

Tero Parviainenvor 4 Monaten

Good question. I don't have an intuition for how stretched latents might decode. Could be an interesting thing to try. I guess the inpainting stuff they have is more ready at hand, where you can insert new parts to a sample rather than stretch.

Profilbild von Pranay Khaire

Pranay Khairevor 4 Monaten

what's the original music?

Profilbild von Tero Parviainen

Tero Parviainenvor 4 Monaten

this loop from splice

Profilbild von Pranay Khaire

Pranay Khairevor 4 Monaten

thanks 🫡

Profilbild von Dallas Rose

Dallas Rosevor 4 Monaten

This is really dope, what's UI? Is it public?

Profilbild von Tero Parviainen

Tero Parviainenvor 4 Monaten

thx! the ui is a hastily vibe coded remix of this

Profilbild von physalisx

physalisxvor 4 Monaten

Nice! Should also be possible to "inpaint" between the samples to create transitions?

Profilbild von Tero Parviainen

Tero Parviainenvor 4 Monaten

Absolutely! Need to experiment with how much inpainting remains on course without prompts, or whether it needs guidance

Profilbild von Joachim Skans

Joachim Skansvor 4 Monaten

amazing

Ähnliche Videos

I'm using an ESP32 to sample the car's existing signal, turn, backup, and stop lamps, and then generate the waveform for a hidden, addressable LED strip:

I'm using an ESP32 to sample the car's existing signal, turn, backup, and stop lamps, and then generate the waveform for a hidden, addressable LED strip:

Dave W Plummer

58,487 Aufrufe • vor 3 Monaten

In this week’s Stability Seconds, we’re showing you how to generate custom, commercially safe audio for your next video project with Stable Audio 2.5 🎵 Here’s how you can do it: ▶️ Find a short video clip that you want to add sound to. ▶️ Prompt Stable Audio 2.5 for genre, overall mood, and instruments that match your video. In our prompt, we used terms like “cinematic,” “awe-inspiring,” and “dramatic horn section.” ▶️ Generate a 3-minute track, then scrub through to find the best cut. ▶️ Add that audio to your clip to create a polished soundtrack. You can learn more and start using Stable Audio 2.5 here 👉

In this week’s Stability Seconds, we’re showing you how to generate custom, commercially safe audio for your next video project with Stable Audio 2.5 🎵 Here’s how you can do it: ▶️ Find a short video clip that you want to add sound to. ▶️ Prompt Stable Audio 2.5 for genre, overall mood, and instruments that match your video. In our prompt, we used terms like “cinematic,” “awe-inspiring,” and “dramatic horn section.” ▶️ Generate a 3-minute track, then scrub through to find the best cut. ▶️ Add that audio to your clip to create a polished soundtrack. You can learn more and start using Stable Audio 2.5 here 👉

Stability AI

12,679 Aufrufe • vor 1 Jahr

MusicHiFi Fast High-Fidelity Stereo Vocoding Diffusion-based audio and music generation models commonly generate music by constructing an image representation of audio (e.g., a mel-spectrogram) and then converting it to audio using a phase reconstruction model or vocoder.

MusicHiFi Fast High-Fidelity Stereo Vocoding Diffusion-based audio and music generation models commonly generate music by constructing an image representation of audio (e.g., a mel-spectrogram) and then converting it to audio using a phase reconstruction model or vocoder.

AK

27,285 Aufrufe • vor 2 Jahren

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵

Mihir Prabhudesai

82,571 Aufrufe • vor 2 Monaten

Turn detection and audio chunk playing is considerably better. Averaging 3GB of URAM to generate and stream the voice locally using Chatterbox-Turbo 🔥🚀

Turn detection and audio chunk playing is considerably better. Averaging 3GB of URAM to generate and stream the voice locally using Chatterbox-Turbo 🔥🚀

Prince Canuma

16,750 Aufrufe • vor 9 Monaten

Need to generate images at scale? Use the BudgetPixel API. Create bulk images, test different styles, generate variations, and bring image generation into your own apps, tools, and workflows faster. Perfect for developers, creators, and teams building with AI.

Need to generate images at scale? Use the BudgetPixel API. Create bulk images, test different styles, generate variations, and bring image generation into your own apps, tools, and workflows faster. Perfect for developers, creators, and teams building with AI.

BudgetPixel AI

1,134,794 Aufrufe • vor 2 Monaten

Opus 5 built this flight simulator in one go. Using only Three.js. The trick to getting this quality and higher (if you prompt harder) seems to be in building a good judge-executor harness. The judge keeps the loop running to improve output quality.

Opus 5 built this flight simulator in one go. Using only Three.js. The trick to getting this quality and higher (if you prompt harder) seems to be in building a good judge-executor harness. The judge keeps the loop running to improve output quality.

elvis

14,333 Aufrufe • vor 1 Monat

Today we’re launching Stable Audio 2.5: The first audio model built for enterprise-grade sound production 🔊 Audio influences brand engagement by 86%, but few enterprises are leveraging audio as an extension of their brand, making customized sound an untapped differentiator. Stable Audio 2.5 is purpose-built for this opportunity to create customizable, high-quality audio at scale, with capabilities that include: ▶️ Improved musical composition: Generate full songs with multi-part structure, meaning a clear intro, middle, and outro. ▶️ Audio inpainting: Input audio, select where the track should start, and the model uses the context to generate the rest of the track. ▶️ Customization: Our team can fine-tune Stable Audio 2.5 to help enterprises create the right sound for their brand. ▶️ Faster inference: The model can generate up to three-minute long tracks in under two seconds on a GPU, outputting in just eight steps (compared to ~50 in the previous model). You can learn more here 👉

Stability AI

68,301 Aufrufe • vor 1 Jahr

In DBeaver 25.0, there is a faster way to generate queries using AI. Simply enter the anand iyer command in the SQL Editor, type your prompt, and execute it.

In DBeaver 25.0, there is a faster way to generate queries using AI. Simply enter the anand iyer command in the SQL Editor, type your prompt, and execute it.

DBeaver

22,731 Aufrufe • vor 1 Jahr

11k people are using the ElevenLabs MCP server in Claude. It connects to your ElevenLabs account and lets you generate speech, sound effects, and music directly in Claude. Generate audio with ElevenLabs without friction.

11k people are using the ElevenLabs MCP server in Claude. It connects to your ElevenLabs account and lets you generate speech, sound effects, and music directly in Claude. Generate audio with ElevenLabs without friction.

ElevenLabs Developers

28,663 Aufrufe • vor 6 Monaten

Here's how to do a bit of VFX work using Seedance 2: If you generate with Seedance 2 you often get a great shot but unfortunately with one or more minor artefacts. Instead of discarding the generation, you can actually edit the video using Seedance 2. In my case it i had to remove a character and I did this using simply as the prompt and using the original video as reference: "Remove boy from video". I then regenerated the missing detail (the boy) using an isolated version of the boy that I removed. And then animated using Seedance 2: "the boy runs sideways and stops. white background. he stays in the center of the screen." In the tutorial below, I'll show how I got rid of an artefact in a shot I liked, and used good old compositing to combine a two videos. As always I'll share the link to the Space below.

Here's how to do a bit of VFX work using Seedance 2: If you generate with Seedance 2 you often get a great shot but unfortunately with one or more minor artefacts. Instead of discarding the generation, you can actually edit the video using Seedance 2. In my case it i had to remove a character and I did this using simply as the prompt and using the original video as reference: "Remove boy from video". I then regenerated the missing detail (the boy) using an isolated version of the boy that I removed. And then animated using Seedance 2: "the boy runs sideways and stops. white background. he stays in the center of the screen." In the tutorial below, I'll show how I got rid of an artefact in a shot I liked, and used good old compositing to combine a two videos. As always I'll share the link to the Space below.

Martin LeBlanc

18,312 Aufrufe • vor 4 Monaten

That's pretty powerful You can turn any YT video into an infographic using Nano Banana Pro in Gemini. - Copy any YT link - Paste in Gemini and ask it to analyze it (Gemini can access the video just using the URL) - Then ask for an infographic Prompt: "Generate an image of an infographic explaining the concept presented in the video."

That's pretty powerful You can turn any YT video into an infographic using Nano Banana Pro in Gemini. - Copy any YT link - Paste in Gemini and ask it to analyze it (Gemini can access the video just using the URL) - Then ask for an infographic Prompt: "Generate an image of an infographic explaining the concept presented in the video."

Paul Couvert

168,434 Aufrufe • vor 10 Monaten

[#OSINT] Using the same chrome extension, this project injects a context menu next to any YouTube video, extracting the video ID to dynamically generate Google search queries and dorks. Designed to reduce friction, eliminate user error, and enhance the browsing experience.

[#OSINT] Using the same chrome extension, this project injects a context menu next to any YouTube video, extracting the video ID to dynamically generate Google search queries and dorks. Designed to reduce friction, eliminate user error, and enhance the browsing experience.

OsintSupport

16,019 Aufrufe • vor 3 Jahren

I just used Luma's text-to-3D to generate a DeLorean from Back to the Future and placed it in my living room using the Vision Pro! The future is wild. 🤩

I just used Luma's text-to-3D to generate a DeLorean from Back to the Future and placed it in my living room using the Vision Pro! The future is wild. 🤩

Ammaar Reshi

265,563 Aufrufe • vor 2 Jahren

Senator Josh Hawley gets Spirit Airlines Vice President Matthew Klein to admit they are using algorithms to charge people different prices for the same seats “Why do you make people enter in their age and their geographic location and their gender before they can even see the cost of a seat — you're using those personal characteristics to generate the fees — You don't need somebody's gender in order to do it. You use it clearly. You're using it to generate the prices” He confirms they are using algorithms for pricing

Senator Josh Hawley gets Spirit Airlines Vice President Matthew Klein to admit they are using algorithms to charge people different prices for the same seats “Why do you make people enter in their age and their geographic location and their gender before they can even see the cost of a seat — you're using those personal characteristics to generate the fees — You don't need somebody's gender in order to do it. You use it clearly. You're using it to generate the prices” He confirms they are using algorithms for pricing

Wall Street Apes

239,186 Aufrufe • vor 6 Monaten

Have been doing some stem remixing work with Stable Audio 3. 📦 Medium model 🔉 init_audio holding the original audio file 😶‍🌫️ init_noise_level between 0.4-0.5 seems to be the sweet spot 🪄 Empty promps

Have been doing some stem remixing work with Stable Audio 3. 📦 Medium model 🔉 init_audio holding the original audio file 😶‍🌫️ init_noise_level between 0.4-0.5 seems to be the sweet spot 🪄 Empty promps

Tero Parviainen

26,716 Aufrufe • vor 3 Monaten

This is Repo Prompt 1.5 The new Context Builder connects to your agent of choice, using your existing subscriptions, to fully automate the process of building the perfect context for a given token budget. All of Repo Prompt's power, fully automated, with 1 click

This is Repo Prompt 1.5 The new Context Builder connects to your agent of choice, using your existing subscriptions, to fully automate the process of building the perfect context for a given token budget. All of Repo Prompt's power, fully automated, with 1 click

eric provencher

195,327 Aufrufe • vor 11 Monaten