Royal Cities
@royalcities.bsky.social
Research, Solutions and Model Design @ Audialab. |
Stream my new release here! https://open.spotify.com/album/3FnXFAI7IGJukQ94zRWsN2
Stream my new release here! https://open.spotify.com/album/3FnXFAI7IGJukQ94zRWsN2
We need more tools that work WITH producers and to me a sample is JUST A SAMPLE - AI or not and its what YOU DO WITH IT that sets you apart as a producer.
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
December 5, 2024 at 6:10 PM
We need more tools that work WITH producers and to me a sample is JUST A SAMPLE - AI or not and its what YOU DO WITH IT that sets you apart as a producer.
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
Just 3 gated examples below.
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
December 5, 2024 at 6:10 PM
Just 3 gated examples below.
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
Supersaw Chord Progressions 👇
December 5, 2024 at 6:09 PM
Supersaw Chord Progressions 👇
Now this is all fun but how about musicality? Well I've shown off a few in the prior videos BUT to cover it more and speak to both musicality and its knowledge of triplet time lets just generate some identical prompts (with triplet and without) and see what comes out!
Arps/Bass 👇
Arps/Bass 👇
December 5, 2024 at 6:09 PM
Now this is all fun but how about musicality? Well I've shown off a few in the prior videos BUT to cover it more and speak to both musicality and its knowledge of triplet time lets just generate some identical prompts (with triplet and without) and see what comes out!
Arps/Bass 👇
Arps/Bass 👇
Here is this in action. 😀
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
December 5, 2024 at 6:09 PM
Here is this in action. 😀
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
For example lets generate a saw arp at 140BPM.
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
December 5, 2024 at 6:09 PM
For example lets generate a saw arp at 140BPM.
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
The crazy part is if you push it higher - you can encourage the AI to be more creative with the sample leading it to change the melody!
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
December 5, 2024 at 6:09 PM
The crazy part is if you push it higher - you can encourage the AI to be more creative with the sample leading it to change the melody!
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
Here's a couple examples of Audio in > Style transfer out.
- and yes the FX can ALSO be transferred 😄
- and yes the FX can ALSO be transferred 😄
December 5, 2024 at 6:09 PM
Here's a couple examples of Audio in > Style transfer out.
- and yes the FX can ALSO be transferred 😄
- and yes the FX can ALSO be transferred 😄
So this is a lot to cover but lets start with some of the fun stuff - AI Style Transfer!
(otherwise known as Audio-to-Audio)
(otherwise known as Audio-to-Audio)
December 5, 2024 at 6:09 PM
So this is a lot to cover but lets start with some of the fun stuff - AI Style Transfer!
(otherwise known as Audio-to-Audio)
(otherwise known as Audio-to-Audio)
This led to EDM Elements - A model capable of generating Supersaw chord progressions, arps, leads, Sine/Bell pluck breaks, Deep House Bass and Square / Saw Leads (ALL WITH built in effects)
🥳
🥳
December 5, 2024 at 6:09 PM
This led to EDM Elements - A model capable of generating Supersaw chord progressions, arps, leads, Sine/Bell pluck breaks, Deep House Bass and Square / Saw Leads (ALL WITH built in effects)
🥳
🥳
📢ATTN Producers & Musicians📢
Today is the release of the most capable FREE open source sample generator tailored for EDM. Its the largest model yet with HIGH musicality & VERY robust AI Style transfer - all while respecting copyright!
ft. a link to get started with it RIGHT NOW😎
Lets dive in!
👇
Today is the release of the most capable FREE open source sample generator tailored for EDM. Its the largest model yet with HIGH musicality & VERY robust AI Style transfer - all while respecting copyright!
ft. a link to get started with it RIGHT NOW😎
Lets dive in!
👇
December 5, 2024 at 6:09 PM
📢ATTN Producers & Musicians📢
Today is the release of the most capable FREE open source sample generator tailored for EDM. Its the largest model yet with HIGH musicality & VERY robust AI Style transfer - all while respecting copyright!
ft. a link to get started with it RIGHT NOW😎
Lets dive in!
👇
Today is the release of the most capable FREE open source sample generator tailored for EDM. Its the largest model yet with HIGH musicality & VERY robust AI Style transfer - all while respecting copyright!
ft. a link to get started with it RIGHT NOW😎
Lets dive in!
👇
We need more tools that work WITH producers and to me a sample is JUST A SAMPLE - AI or not and its what YOU DO WITH IT that sets you apart as a producer.
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
December 5, 2024 at 6:01 PM
We need more tools that work WITH producers and to me a sample is JUST A SAMPLE - AI or not and its what YOU DO WITH IT that sets you apart as a producer.
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
Mangle them, keep them as is, chop them up, pitch / formant shift them - it's up to you as an artist - just have fun!
Just 3 gated examples below.
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
December 5, 2024 at 6:01 PM
Just 3 gated examples below.
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
All effects (reverb, gate, and filter sweeps) can be prompted together or separately of course.
And yes all gates ARE Tempo Synced 😎
Supersaw Chord Progressions 👇
December 5, 2024 at 6:01 PM
Supersaw Chord Progressions 👇
Now this is all fun but how about musicality? Well I've shown off a few in the prior videos BUT to cover it more and speak to both musicality and its knowledge of triplet time lets just generate some identical prompts (with triplet and without) and see what comes out!
Arps/Bass 👇
Arps/Bass 👇
December 5, 2024 at 6:01 PM
Now this is all fun but how about musicality? Well I've shown off a few in the prior videos BUT to cover it more and speak to both musicality and its knowledge of triplet time lets just generate some identical prompts (with triplet and without) and see what comes out!
Arps/Bass 👇
Arps/Bass 👇
Here is this in action. 😀
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
December 5, 2024 at 6:01 PM
Here is this in action. 😀
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
Note how "fast speed" just means MORE chord progressions and melody switch ups in the same time intervals while slow is fewer.
We're slowly getting better control with the AI rather than just hoping for the best!
(Both are in G minor / 128BPM btw)
For example lets generate a saw arp at 140BPM.
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
December 5, 2024 at 6:00 PM
For example lets generate a saw arp at 140BPM.
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
The prompt is IDENTICAL minus 1 change - the text slow, medium & fast speed.
As long as we include the same BPM the model understands the difference relates to how often the notes are being subdivided.
So lets see that in action!
The crazy part is if you push it higher - you can encourage the AI to be more creative with the sample leading it to change the melody!
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
December 5, 2024 at 6:00 PM
The crazy part is if you push it higher - you can encourage the AI to be more creative with the sample leading it to change the melody!
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
Here is that in action!
Input Audio - > noise 1.6 version -> noise 1.8 version.
i.e.
Original - > straight conversion -> creative conversion.
Here's a couple examples of Audio in > Style transfer out.
- and yes the FX can ALSO be transferred 😄
- and yes the FX can ALSO be transferred 😄
December 5, 2024 at 6:00 PM
Here's a couple examples of Audio in > Style transfer out.
- and yes the FX can ALSO be transferred 😄
- and yes the FX can ALSO be transferred 😄
So this is a lot to cover but lets start with some of the fun stuff - AI Style Transfer!
(otherwise known as Audio-to-Audio)
(otherwise known as Audio-to-Audio)
December 5, 2024 at 6:00 PM
So this is a lot to cover but lets start with some of the fun stuff - AI Style Transfer!
(otherwise known as Audio-to-Audio)
(otherwise known as Audio-to-Audio)
This led to EDM Elements - A model capable of generating Supersaw chord progressions, arps, leads, Sine/Bell pluck breaks, Deep House Bass and Square / Saw Leads (ALL WITH built in effects)
🥳
🥳
December 5, 2024 at 6:00 PM
This led to EDM Elements - A model capable of generating Supersaw chord progressions, arps, leads, Sine/Bell pluck breaks, Deep House Bass and Square / Saw Leads (ALL WITH built in effects)
🥳
🥳