Altinus (@Altius__) header
Altinus (@Altius__) profile picture

Altinus

@Altius__

hello

Joined December 2021
  • Tweets222
  • Following143
  • Followers769
68Media
Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)Photo by Altinus (@Altius__)
Depth-aware light injection in TypeGPU I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step Inference, lighting and draw all go through the same command encoder.
956
4,657
1,285
49,814
10,116,945
Altinus retweeted
Nasko (@Naskomusic) profile picture
Nasko@NaskomusicJul 9
Midi-tracked spectral suppression ✨ Keytrack based on the last midi note you pressed! 🥳 SILK dropping this week 🫡
8
9
1
230
8,449
ORAM ✿ open-source generative looper ✿
2
12
153
5,916
PureData modal synthesis v0002
1
4
20
944
new #puredate patch download it here: patreon.com/c/ArtiomConstant… #idm #puredatagem #sounddesign #audioreactive #audiovisual #glitch #vectorheart #newmediaart #creativecoding #pd #y2k
2
8
30
1,185
M4LのLive Amp Modelerやばいかも、 設定なんも詰めてないのにAbleton付属だけでこんないい音出ていいんだ…これからこれでRecしようかな…
4
11
273
25,450
Altinus retweeted
Massimo (@Rainmaker1973) profile picture
Massimo
@Rainmaker1973May 15
Fast Fourier Analysis in action. Any complex waveform, sound, or shape can be perfectly reconstructed as the sum of simple rotating circles (epicycles).
66
1,474
126
7,418
1,120,252
100% synthesized ambience in plugdata. Shout out Amfivolía's tutorials, awesome stuff.
7
11
1
224
11,410
FDNリバーブの直行行列をアダマール行列から、ランダム直交行列での実装で試してみました👀 8ディレイラインのFDNなので音質は16や32に比べてまだですが良い感じです👀 事前にPythonなどでQR分解でランダム直交行列を作成して用いています👀
1
6
45
2,933
💥MaxでAIと宇宙を表現？ 藝大Maxサマースクール2026開催！ 東京藝術大学が開催する、Cycling '74 Maxを軸とした「AIと宇宙」がテーマのハイブリッド型ワークショップ。 ✅ 超初級から上級まで4段階の体系的カリキュラム ✅ FluCoMaによる音響特徴量抽出と機械学習の活用 ✅「AIエージェントの発想に接続する」高度な実装 ✅参加者にはMax+RNBOの100日間ライセンスを付与 　 詳細な開催概要はリプ欄から👇
Image from サウンド＆レコーディング・マガジン（サンレコ）公式 (@snrec_jp)
1
7
1
17
9,014
No more webview! Still a lot of issues, but it's getting there
1
2
1
44
12,177
Altinus retweeted
DeepSeek (@deepseek_ai) profile picture
DeepSeek
@deepseek_aiApr 24
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/D… 🤗 Open Weights: huggingface.co/collections/d… 1/n
Image from DeepSeek (@deepseek_ai)
1,649
7,433
2,421
45,334
10,173,120
Altinus retweeted
Altinus (@Altius__) profile picture
Altinus@Altius__Feb 4
[biquads~]
4
10
154
6,205
Altinus retweeted
JUCE (@JUCElibrary) profile picture
JUCE@JUCElibraryMar 24
Check out our interview with Evan from @anukarimusic about audio on the GPU, his innovative physics-based synth Anukari, and innovation in audio plugins. juce.com/made-with-juce/evan…
Evan from Anukari - JUCE

Evan from Anukari - JUCE

An ex-Googler with a dream: Evan helped pave the way for low-latency audio on the GPU with his innovative synth

juce.com
1
9
27
1,626
Image from あにめる (@animel7316)
9
470
4
5,564
79,188
Altinus retweeted
AluanWang (@IOivm) profile picture
AluanWang
@IOivmMar 10
InkField | 墨域 is about to be released. From the first version, both humans and bots will be able to create on it together. In a way, the system reflects the time we live in. Humans and machines are already living in a kind of symbiosis. I’m generally an optimistic person. But I have to admit, 2026 feels a little heavy right now. Maybe the work will reflect that. Maybe it won’t. Either way, wishing everyone well. I still believe the dawn is coming.
26
192
7
2,193
112,143
春节快乐 春節おめでとうございます
Image from ぬ絵 (@nullnull_syntax)
122
1,488
129
7,600
332,401
Altinus retweeted
Altinus (@Altius__) profile picture
Altinus@Altius__22 Oct 2025
room response generator based on the Image Method Implemented using pdlua, of course with the help of ai🤡
2
4
33
1,520
無料で「Suno v4.5」超え？　音楽生成AI「ACE-Step v1.5」公開　個人向けGPUでも動作 itmedia.co.jp/aiplus/article…
無料で「Suno v4.5」超え？ 音楽生成AI「ACE-Step v1.5」公開 個人向けGPUでも動作

無料で「Suno v4.5」超え？　音楽生成AI「ACE-Step v1.5」公開　個人向けGPUでも動作

AIスタートアップの米Timedomainが音楽生成AI「ACE-Step v1.5」を公開した。「RTX 3090」など消費者向けのGPUでも動作し、同様の音楽生成AI「Suno」の前世代モデル「v4.5」を上回る性能とうたう。MITベースの独自ライセンスで、商用利用や配布、複製が可能だが、利用者に対して規約として芸術的誠実性や法令順守を求めている。

itmedia.co.jp
1
99
16
531
49,051
machine pareidolia - noise into sample and hold into rave (trained on speech) into whisper. whisper is printing what it interprets from the last chunk of audio.
8
2
82
4,300
Load more