Generate a plurality of sonic constellations with A.I. ⚫️ Developed by @hexorcismos Inquiries at hola@semilla.ai
Joined July 2022
- Tweets 61
- Following 1
- Followers 594
- Likes 88
13 Photos and videos
Pinned Tweet
14 Nov 2023
SEMILLA.AI v1 is out now!
You can download here (download link in description):
hexorcismos.bandcamp.com/mer…
We made this video which expains the process and research behind it...
youtu.be/_2C3XeQgGtY
We hope you enjoy this AI music synthesis tool!
5
13
78
14,840
Jun 12
Lately, we been been feeling a shift in AI music.
The latest most popular systems are offline: you write a prompt, you wait, a finished, derivative .wav is generated.
Now the models are learning to play in time with us. En vivo.
Here’s survey of the new realtime wave 🧵👇
2
1
6
1,187
Jun 12
The tools are open:
❉ train on your own music → CoDiCodec-Flow
❉ jam today → Magenta RealTime 2 apps
❉ the accompanist → LiveBand
❉ stream your diffusion models → LMDM
❉ patch into Max/Pd → RAVE
1
1
91
Jun 12
We are really excited about the potential new sonic expressions that these tools will enable for the live context, installation, performances and other new spaces !
What will be the new music styles?
Let’s hack these tools & listen! 🔊🔊🔊
61
ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. retweeted
May 22
Just added a Google Colab notebook to the CoDiCodec-Flow repo.
You can train your own real-time neural audio synthesis model with about 2-3 hrs. of audio and get results in about 3 hours of training time.
Small Data models > Corporate Big Tech models
github.com/moiseshorta/CoDiC…
2
33
1,177
ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. retweeted
May 15
Today I'm open sourcing CoDiCodec-Flow, a generative audio model for real-time neural audio synthesis.
github.com/moiseshorta/CoDiC…
After 5 years and many gigs performing with RAVE, I always found that there was a lack in sound and expressive quality; CoDiCodec-Flow improves that...
2
2
20
482
ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. retweeted
17 Jul 2024
the new stuff doesn't happen in the model or just using the model by itself, but the interaction between the human and the model - @hexorcismos
in this ep
- his works using ai: Okachihuali, Mutalismx
- building @semilla_ai
- latent interpolation
- creativity x ai
- music ai
1
2
12
2,047
ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. retweeted
17 Jul 2024
Full EP:
spotify - open.spotify.com/episode/779…
substack - redito.substack.com/p/decodi…
2
3
616
ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. retweeted
model jam
1
2
9
851
ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. retweeted
8 Mar 2024
@Kloxiimusic, @SiminaOprescu, @PortraitXO and more open up about their creative processes using @hexorcismos’ @semilla_ai tool for the ‘MUTUALISMX’ VA. mixmag.asia/feature/mutualis…
2
2
371
How @hexorcismos’ collaborative project ‘MUTUALISMX’ challenges AI prejudices
mixmag.net/feature/mutualism…
1
5
9,413
20 Feb 2024
Thank you @MixmagAsia Asia for the mention!
20 Feb 2024
@hexorcismos’ VA out via @nicolas___jaar’s @_otherpeople centres around @semilla_ai, a neural audio synthesis tool created by Hexorcismos himself. mixmag.asia/read/hexorcismos…
266
ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. retweeted
15 Feb 2024
𝔐ᴜᴛᴜᴀʟɪsᴍ𝔛 is officially out on @_otherpeople via all streaming services and as 2xLP !
The making of this album been a planetary-spanning journey where a generative music collaboration emerged through time and space via technologies of “sonic becoming” with @semilla_ai
2
6
31
5,768