Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

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

9,816 subscribers

26,716 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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.

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

10,879 views • 3 months ago

I've been really wanting to work on video game audio as of recently, so I re-designed ALL of the audio for this VALORANT short. I deleted the original audio and re-imagined it with my own sounds, music, and brought on voice actors. Wouldn't it be cool if Riot Games saw this?

I've been really wanting to work on video game audio as of recently, so I re-designed ALL of the audio for this VALORANT short. I deleted the original audio and re-imagined it with my own sounds, music, and brought on voice actors. Wouldn't it be cool if Riot Games saw this?

Luke Dimond

16,509 views • 3 years ago

The reception since we launched the first unified audio + text + image to video model in production last week has been incredible! We wanted to take a moment and highlight some firsts: - the first omnimodal modal that jointly operates over text, image, and audio. Fun fact: we shipped our first audio-to-video model Character-1 last June! - Character-3 is generating 5 minute uncut clips, and capable of temporally stable longform prediction. - Character-3 handles realistic humans, cartoons, side profiles, dynamic backgrounds, anime, animals, and more. - Character-3 sets a new standard for fast & efficient video diffusion at HD and SD resolutions, leveraging our advancements in realtime video generation. We'll have an announcement soon, but you can read more about an earlier version of this line of work in our paper here:

The reception since we launched the first unified audio + text + image to video model in production last week has been incredible! We wanted to take a moment and highlight some firsts: - the first omnimodal modal that jointly operates over text, image, and audio. Fun fact: we shipped our first audio-to-video model Character-1 last June! - Character-3 is generating 5 minute uncut clips, and capable of temporally stable longform prediction. - Character-3 handles realistic humans, cartoons, side profiles, dynamic backgrounds, anime, animals, and more. - Character-3 sets a new standard for fast & efficient video diffusion at HD and SD resolutions, leveraging our advancements in realtime video generation. We'll have an announcement soon, but you can read more about an earlier version of this line of work in our paper here:

Hedra

180,676 views • 1 year ago

We just tested a lip sync workflow in Seedance 2.0… and it might actually compete with HeyGen and other avatar models 👀 You upload: – a reference image – a blacked out video with audio OR audio file – a prompt (camera motion + VO) The prompted VO is really important here to make sure the model doesn’t hallucinate or riff off of the original speaker verses. Feels like a legit breakthrough. Lip sync has been a pain point for a while, and this gets us a lot closer.

Curious Refuge

19,504 views • 4 months ago

CW: audio, digestion It took me a while and with some complications but I have finished this animation! :3 digesting a prey while you sleep can be really satisfying and the gurgly noises can be very relaxing!, plus you don't have to worry about lunch, maybe...~

Sensitive content

CW: audio, digestion It took me a while and with some complications but I have finished this animation! :3 digesting a prey while you sleep can be really satisfying and the gurgly noises can be very relaxing!, plus you don't have to worry about lunch, maybe...~

FinniA

101,088 views • 2 years ago

5 minutes of Battlefield 6 footstep audio playing too late, in the wrong spot or not at all. Make sure to use headphones when watching this. This has been one of my top 3 issues since the beta. We shouldn't still be dealing with this nearly a year later.

5 minutes of Battlefield 6 footstep audio playing too late, in the wrong spot or not at all. Make sure to use headphones when watching this. This has been one of my top 3 issues since the beta. We shouldn't still be dealing with this nearly a year later.

Nickel

106,663 views • 1 month ago

Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now available in early access (link below). Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.

Introducing FLUX 3. One multi-modal model for Image, Video, Audio and Action-Prediction. Creations are truer to life in every kind of style. FLUX 3 Video is now available in early access (link below). Jointly trained in one unified architecture, our model can be extended to predict actions for robotics. See our work with mimic and Audi in the thread.

Black Forest Labs

1,212,670 views • 1 month ago

I have playing with Black Forest Labs Black Forest Labs FLUX 3 for a few days now. (Thank you for the early access!) And I played with it... a lot. Some may say, too much. 😅 Here are some of my favorite gens. Needless to say, I love this model. Audio on! More in 🧵

I have playing with Black Forest Labs Black Forest Labs FLUX 3 for a few days now. (Thank you for the early access!) And I played with it... a lot. Some may say, too much. 😅 Here are some of my favorite gens. Needless to say, I love this model. Audio on! More in 🧵

Ostris

31,795 views • 1 month ago

Bob Myers, on the difficulty of building a team with 3 max contracts: "The truth is, depth may be more important than it's ever been...We gotta be honest of can this model work. Depth is key, and you only have a certain amount of resources to spend."

Bob Myers, on the difficulty of building a team with 3 max contracts: "The truth is, depth may be more important than it's ever been...We gotta be honest of can this model work. Depth is key, and you only have a certain amount of resources to spend."

PHLY Sixers

77,674 views • 4 months ago

MICROPHONE UPDATE: Charlie was wearing a Rode Wireless PRO, which comes standard with a lapel magnet, 2 storage cases + computer dock, 32-bit sound, and internal device recording & storage. ▪️The moment that mic was removed from its case, it was recording. ▪️The mic could only be turned off remotely—neither Charlie nor the security team could have turned it off. ▪️All audio was captured & recorded on the mic itself. The 32-bit sound captures quiet whispers, loud shouts & everything in between. ▪️Mikey McCoy filmed a close-up video of Charlie getting mic'd up. Mikey, where's that video? Hey Philip Goldsberry and Terryl Farnsworth: where's Charlie's audio from that day? The public has a right to hear that audio. More importantly, it's holding extremely valuable evidence. (unless it was exploded, in which case those 32-bit recordings would be completely gone...). Is there audio from immediately after Charlie's death? Who else thinks TPUSA should have to release that audio?

MICROPHONE UPDATE: Charlie was wearing a Rode Wireless PRO, which comes standard with a lapel magnet, 2 storage cases + computer dock, 32-bit sound, and internal device recording & storage. ▪️The moment that mic was removed from its case, it was recording. ▪️The mic could only be turned off remotely—neither Charlie nor the security team could have turned it off. ▪️All audio was captured & recorded on the mic itself. The 32-bit sound captures quiet whispers, loud shouts & everything in between. ▪️Mikey McCoy filmed a close-up video of Charlie getting mic'd up. Mikey, where's that video? Hey Philip Goldsberry and Terryl Farnsworth: where's Charlie's audio from that day? The public has a right to hear that audio. More importantly, it's holding extremely valuable evidence. (unless it was exploded, in which case those 32-bit recordings would be completely gone...). Is there audio from immediately after Charlie's death? Who else thinks TPUSA should have to release that audio?

Sam Parker 🇺🇸🧯

676,487 views • 8 months ago

📢🚨 For those of you that like to play with these videos and slow it down and do closeups and all that. Have fun. The first video set is untouched. The second and third run are slowed down. The fourth is black and white closeup. No audio has been altered from the original. Some thinks it's AI. Others don't. Some aren't sure. Let me know your thoughts on it. Repost and Like.

📢🚨 For those of you that like to play with these videos and slow it down and do closeups and all that. Have fun. The first video set is untouched. The second and third run are slowed down. The fourth is black and white closeup. No audio has been altered from the original. Some thinks it's AI. Others don't. Some aren't sure. Let me know your thoughts on it. Repost and Like.

TriggerSmart

221,376 views • 3 months ago

This Is Absolutely Mind Blowing ⚠️ Barack Obama’s New Movie, Leave The World Behind, When Downloaded & Put Into An Editing Program Has 4 Audio Files Instead Of The Standard 1 One Of The Audio Files Is Just A Frequency 🚨 “Low Frequency Infrasound” Other Movies Do Not Have This. The Guy Has Done Thousands Of Movies & Never Seen This “When you open this this movie right here is Jurassic Park, for instance. Okay? I'm just showing this to people who have never seen this. For the last 15 years that I have been using Sony Vegas and other editing software and have gone through downloading movies And using them in our own video production, 100% of the time, it's either an MKV or a MP For occasionally, you'll download a torrent that's in AVR, but not very often. And this is what it will always look like. One video file right here. One audio file right here always. That's been my experience. Now let me show you what happened when we downloaded and put, Sony put the, uh, movie Leave the World Behind onto Sony Vegas. Here you go. Stunning. Stunning. One video file, 4 audio files opened up. And this one, This 4th audio file seems to be the weapon. This is a low ex uh, ELF, Uh, Low Frequency Infrasound. Infrasonic wave right here. And, um, so we We are gonna let me put the camera back on again. So this is big news just just so people realize. In in 15 years of video editing, I have never downloaded now speaking specifically a movie file. Okay. A Hollywood movie from a torrent downloading it in either MKV, MP4, occasionally AVI. 100% of the time, over a thousands movies I've done this with, you have video file, audio file, period. This is the very first time I've ever seen anything like this with the 4 files. Bonnie's gonna go into now talking about the The infrasonic sound waves and what we found out about that and the fact that there's one here. We're in the point is we're going to go back after Bonnie gives you some information about what it is we're dealing with, how this is a weapon. Then we're gonna go back, uh, towards the end of the live stream here. And I'm gonna hit specific places where this weapon was used against anybody who watches it. Okay.”

This Is Absolutely Mind Blowing ⚠️ Barack Obama’s New Movie, Leave The World Behind, When Downloaded & Put Into An Editing Program Has 4 Audio Files Instead Of The Standard 1 One Of The Audio Files Is Just A Frequency 🚨 “Low Frequency Infrasound” Other Movies Do Not Have This. The Guy Has Done Thousands Of Movies & Never Seen This “When you open this this movie right here is Jurassic Park, for instance. Okay? I'm just showing this to people who have never seen this. For the last 15 years that I have been using Sony Vegas and other editing software and have gone through downloading movies And using them in our own video production, 100% of the time, it's either an MKV or a MP For occasionally, you'll download a torrent that's in AVR, but not very often. And this is what it will always look like. One video file right here. One audio file right here always. That's been my experience. Now let me show you what happened when we downloaded and put, Sony put the, uh, movie Leave the World Behind onto Sony Vegas. Here you go. Stunning. Stunning. One video file, 4 audio files opened up. And this one, This 4th audio file seems to be the weapon. This is a low ex uh, ELF, Uh, Low Frequency Infrasound. Infrasonic wave right here. And, um, so we We are gonna let me put the camera back on again. So this is big news just just so people realize. In in 15 years of video editing, I have never downloaded now speaking specifically a movie file. Okay. A Hollywood movie from a torrent downloading it in either MKV, MP4, occasionally AVI. 100% of the time, over a thousands movies I've done this with, you have video file, audio file, period. This is the very first time I've ever seen anything like this with the 4 files. Bonnie's gonna go into now talking about the The infrasonic sound waves and what we found out about that and the fact that there's one here. We're in the point is we're going to go back after Bonnie gives you some information about what it is we're dealing with, how this is a weapon. Then we're gonna go back, uh, towards the end of the live stream here. And I'm gonna hit specific places where this weapon was used against anybody who watches it. Okay.”

Wall Street Apes

3,769,476 views • 2 years ago

ADMIN POST - PLAY THE AUDIO FILE BELOW I can now confirm that Tommy has actually been released, he is on bail, and the police have taken his phone. I want thank everyone (as does Tommy) who have been out protesting for him today, it absolutely made a difference. Tommy has asked me to upload the conversation he had with his ex wife while he was detained for terror related offences. We will be able to update you all tomorrow.

ADMIN POST - PLAY THE AUDIO FILE BELOW I can now confirm that Tommy has actually been released, he is on bail, and the police have taken his phone. I want thank everyone (as does Tommy) who have been out protesting for him today, it absolutely made a difference. Tommy has asked me to upload the conversation he had with his ex wife while he was detained for terror related offences. We will be able to update you all tomorrow.

Tommy Robinson 🇬🇧

1,816,990 views • 2 years ago

“Thank God Peller clarified. I was just bantering. I only wanted to show people that the UK is not Nigeria; things work differently here. For those saying I have been doing the same thing, there is a difference between criticism and defamation. Peller should be careful with Pastor Tobi.” — Solomon Buchi

“Thank God Peller clarified. I was just bantering. I only wanted to show people that the UK is not Nigeria; things work differently here. For those saying I have been doing the same thing, there is a difference between criticism and defamation. Peller should be careful with Pastor Tobi.” — Solomon Buchi

CHUKS 🍥

206,221 views • 9 days ago

Bytedance is dropping the best video gen model in the world in early July: Seedance 2.5! The video below (audio on) is the launch video from their Volcano Engine conference this week. It cements China’s absolute dominance in video. — 2x’d generation length of all previous models to 30s, with audio + 4k video — >5x’d reference images / audio / video to 50 — Allows localized editing (specific characters, closing, detail), will come with copyright filter Seedance 2 is already the #1 video model and does a whopping $2B in ARR, in a mere 4.5mos! At the current pricing of $2.5/15s, that implies >3.3M hours of video (!) have been generated. That’s 3x every feature film ever made and dozens of Netflixes. Only 3 US AI startups make more revenue. We are 2x’ing realistic video gen length every 6mos. — May 2025: Veo 3 does audio + video for the first time, 15s — Jan 2026: Kling 3 does 15s — Feb 2026: Seedance 2 does 15s, big quality bump — July 2026: 2.5 will do 30s In 18mos, entire music videos will be oneshotted by AI. China continues to extend its lead on video models vs America.

Bytedance is dropping the best video gen model in the world in early July: Seedance 2.5! The video below (audio on) is the launch video from their Volcano Engine conference this week. It cements China’s absolute dominance in video. — 2x’d generation length of all previous models to 30s, with audio + 4k video — >5x’d reference images / audio / video to 50 — Allows localized editing (specific characters, closing, detail), will come with copyright filter Seedance 2 is already the #1 video model and does a whopping $2B in ARR, in a mere 4.5mos! At the current pricing of $2.5/15s, that implies >3.3M hours of video (!) have been generated. That’s 3x every feature film ever made and dozens of Netflixes. Only 3 US AI startups make more revenue. We are 2x’ing realistic video gen length every 6mos. — May 2025: Veo 3 does audio + video for the first time, 15s — Jan 2026: Kling 3 does 15s — Feb 2026: Seedance 2 does 15s, big quality bump — July 2026: 2.5 will do 30s In 18mos, entire music videos will be oneshotted by AI. China continues to extend its lead on video models vs America.

Deedy

70,213 views • 2 months ago

I’ve been playing around with the idea of using my VTube model to make some videos. It feels easier to talk when I don’t have to worry about what’s showing on the webcam😌 Also yep, it’s always going to be in Italian. I’m thinking about doing a little “let’s chat” on my Discord server, maybe even stream sometimes, but it’ll all be in Italian.

I’ve been playing around with the idea of using my VTube model to make some videos. It feels easier to talk when I don’t have to worry about what’s showing on the webcam😌 Also yep, it’s always going to be in Italian. I’m thinking about doing a little “let’s chat” on my Discord server, maybe even stream sometimes, but it’ll all be in Italian.

Ruby

37,979 views • 1 year ago

Unfortunately X seems to have an obsession with throttling Grok produced original content. I have never, not once, under any circumstances, had any of my Grok created content break containment. Ever. And I want to be clear what I mean when I say ever. I've been doing this since the very beginning. Adding anything Grok made to my posts is the kiss of death where exposure is concerned. Please tell me why.

Unfortunately X seems to have an obsession with throttling Grok produced original content. I have never, not once, under any circumstances, had any of my Grok created content break containment. Ever. And I want to be clear what I mean when I say ever. I've been doing this since the very beginning. Adding anything Grok made to my posts is the kiss of death where exposure is concerned. Please tell me why.

BLACK DUMPLING™

11,449 views • 4 months ago