@2g

podcastin n codin thangs like https://xitter.cf/t.co/rN8EECi5l0 hascillators etc

 tokyo japan
sarigama.namaste.jp/nipples/
Joined April 2007
  • Tweets3.3K
  • Following192
  • Followers162
880Media
microPPL retweeted
Tanuj
@tanujnotesSep 21
I wonder if @GrapheneOS can go Omarchy route - fully customizable agent driven OS.
1
4
408
YuE2 🎶🎵 Comfy Support an open music generation model with frontier song quality competitive with Suno v5/v6,Turn lyrics and a style prompt into a complete song with vocals and accompaniment, then shape its melody and chords through an editable score 👇 huggingface.co/Comfy-Org/YuE…

Comfy-Org/YuE2 · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
2
15
154
8,696
theDAW (creator @gantasmo) is an amazing AI-powered DJ app that runs 100% locally on your PC (All OS supported) Built on Stable Audio 3 for audio generation, plus Magenta RealTime 2, Suno & Google Lyria integration. Also interoperable with Ableton, Reaper, Resolume, etc.
8
24
3
323
21,069
Good news for AI music creators. The US Justice Department has backed the argument that training AI on copyrighted material can constitute fair use, recognising the creative possibilities and public benefits of AI. Major implications for AI music. apnews.com/article/justice-d…
16
146
49
385
42,525
microPPL retweeted
青龍聖者
@bdsqlszAug 29
A significant amount of Suno AI's source data has been leaked. Upon investigation, it was found that: Their primary tech stack is MERT25, and they’ve used web crawlers to gather a large amount of YouTube Music content....
25
216
27
2,355
351,558
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.
337
869
384
6,234
1,218,841
microPPL retweeted
Pavel Durov
@durovJul 21
🌍 This summer will see the largest rollout of a non-custodial crypto wallet in human history. ⚡️Instant zero-fee crypto transactions for over a billion users are about to become reality. We're bringing a native non-custodial Gram wallet to every Telegram app! 💎
1,027
1,491
388
12,497
1,015,417
Pinokio 8.0.35 Release Your favorite local AI app launcher got a few bug fixes and some additions including: 1. Ask @grok Ask Grok anything about any app you have installed--Fix broken installs, ask how to use the app, and even use the app itself using natural language!
2
7
1
61
6,595
microPPL retweeted
Tanuj
@tanujnotesJul 17
Today is 6 year anniversary of Olauncher! 🥳 To celebrate, I'm releasing a new, free and open-source, app to fix the gesture navigation issue on phones that don't support gestures on downloaded launchers. github.com/tanujnotes/Ogestu…

GitHub - tanujnotes/Ogesture: Use gesture navigation with third-party launchers on any Android...

Use gesture navigation with third-party launchers on any Android phone. - tanujnotes/Ogesture

github.com
5
3
1
17
1,611
microPPL retweeted
Tanuj
@tanujnotesJul 13
If you're using Olauncher (or any launcher) on a Xiaomi phone, which disables the gesture navigation for third-party launchers, please DM me. I'm working on a solution and need testers. Thank you!
1
2
10
349
I don't say this often, but I'm BEGGING you to try this. Generate images, videos, voice, songs, as easy as scrolling social media. So intuitive, yet so powerful. Anything you could imagine is pretty much there. Built on WanGP (from @deepbeepmeep), all the efficiencies included.
Blaine Brown
@blizaineJul 8
Finally! Say hello to Maestro! Describe a music video or short film, and it makes the whole thing: original song, plans every shot, screenplays, generates the clips, & cuts it all together. 100% Local. No cloud, no subscription. FREE. One-click install via Pinokio. 🧵
20
41
3
364
38,334
Run Stable Audio 3 on ANY Computer with NO VRAM 1-click launcher for the official Stable Audio 3 gradio app. 1. Cross Platform: Works on ALL OS (Mac, Linux, Windows) out of the box 2. No GPU Needed: Even runs on CPU. 3. Ultra Fast: Generate a 2 minute clip in split seconds
Stability AI
@StabilityAIMay 20
Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇
13
42
4
308
73,254
Yeah i think THAT is what StableAudio3 is for. Realtime/Infinite generation. Looking forward to seeing all kinds of experiments!
@TheINAOG
@TheINAOGMay 21
Replying to @cocktailpeanut
look so interesting to add into game/app/development workflow. I always need to search public domain sounds.. I will try it this weekend (I will try to create some interesting pinokio repo too)
3
13
2,837
YES
sui
@birdaboApr 26
A JAPANESE DEV BUILT AN APP THAT SHOWS A FAT CAT ON THE SCREEN AND FORCES YOU TO TAKE A BREAK.
1
1
39
12,350
Google's Gemini in Chrome now lets you save prompts as "skills" thenewstack.io/gemini-chrome…

Google's Gemini in Chrome now lets you save prompts as "skills"

Google's Gemini in Chrome can now save and reuse your favorite AI prompts — here's how it works and how it stacks up against Claude and ChatGPT.

thenewstack.io
1
392
microPPL retweeted
CNX Software
@cnxsoftApr 25
MP3 player and Internet radio player for the @lilygo9 T-LoRa Pager. cnx-software.com/2026/04/25/… The Melody Machine is an open-source Arduino firmware for the ESP32-S3-based T-LoRa Pager messaging device. You can add MP3 audio files and M3U radio playlists, and use the built-in keyboard for controls.
6
2
57
4,552
Check out the DC-ROMA RISC-V Mainboard III for #Framework Laptop 13 in action, running the Qwen3 30B large language model with llama.cpp. #riscv #qwen #llama
1
8
2
89
13,137
Meet Lyra-2.0. This isn't just another AI model. It's a breakthrough in high-fidelity, real-time audio generation. Think instant, studio-quality sound from text, for games, assistants, and more. The community is buzzing because it solves a huge bottleneck: natural voice at scale.
4
15
1
151
10,554
microPPL retweeted
ACE Music
@acemusicAIApr 8
ACE-Step-1.5-xl is out now. We scaled the DiT decoder to 4B. And it shows better audio quality, better prompt following, and better musicality. It still fast -- 8 steps with turbo distillation. What didn't change: - Same generation API, same LoRA training code, same everything - All LM models (0.6B / 1.7B / 4B) fully compatible with all 3 variants - Your existing projects work with XL — no changes needed Try it for free at acemusic.ai Weithgts and code: GitHub: github.com/ace-step/ACE-Step… Hugging Face: huggingface.co/ACE-Step/Ace-… (3 variants: xl-base, xl-sft, xl-turbo) XL demos: ace-step.github.io/ace-step-…
15
77
18
375
36,287
microPPL retweeted
Adina Yakup
@AdinaYakupApr 7
ACE-Step 1.5 XL🎵 New open music generation model is now on @huggingface Model: huggingface.co/collections/A… Demo: huggingface.co/spaces/ACE-St… ✨ 4B DiT - Base/Sft/Turbo ✨ MIT license ✨ Commercial-ready: legally compliant datasets ✨ Full support: Text2Music, Cover, Repaint, Extract, Lego, Complete

Ace-Step 1.5-xl - a ACE-Step Collection

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
7
46
4
259
18,404
Load more