@pariscestchiant nothing beats the feeling of having your tool work exactly as you want
English
TBD
7.6K posts
TBD
@tbdr
creating tools that makes you happy
Romania Katılım Nisan 2008
891 Takip Edilen621 Takipçiler
An open source text to sample music model, with samples you can easily loop.
A really clever concept.
Now I need to vibe code a UI layer.
RoyalCities@RoyalCities
After months of work, today I’m releasing Foundation-1. A SOTA text-to-sample model built specifically for music production workflows. It may also be the most advanced AI sample generator currently available - open or closed. • ~7 GB VRAM • Entirely local • 100% free 😁
English
@tbdr There should be less latency now. Thinking of adding more presets soon to skip the wait.
English
I made an endless focus soundtrack for my work sessions. Each sound is uniquely generated. It's phenomenal for locking in.
English
@tbdr Admittedly, I haven't tested the contributor workflow 😅
I bet if you threw Claude a prompt it'd probably say something like "Oh yeah, Eric's trying to sign it in dev which is a no-no!"
🤖 "Clone github.com/ericclemmons/a… and fix it so I can run it myself locally"
English
🗣️ + @opencode = ⚡
Slop-forked superwhisper so I could have fire-and-forget prompts throughout my day.
↧ Hold to transcribe prompt
⇵ Tap to record prompt
📸 (Optional) Add Screenshots
⇵ Tap again to stop recording
✨ [Enter] for New Session or ⇅ to add to existing
English
@ericclemmons unlimited doors open - managed to implement dozens of ideas that were on the backlog for years. the energy boost you get from doing your own things is truly amazing!
English
Dang it.
Excitement is contagious.
I heard a great idea today and now I can’t sleep because I’m thinking through how to make it happen.
English
TBD retweetledi
🚨 800 FREE CREDITS — 24 HOURS ONLY
We just launched LTX-2.3, our most powerful video model yet. High-res. Fast. Cinematic. Native lip-sync.
Follow + Retweet this post to get 800 credits sent to your DMs.
English
This is how the SVG looks in the @QuiverAI viewer, and how you can export it as a cool animated drawing in MP4.
Try it now at app.quiver.ai
English
@andrewfarah maybe because I am using uv python to handle my multiple python installations (edge case)
English
@tbdr that screen could be clearer. but … you haven’t successfully downloaded the voice model yet.
try that blue download button again and let me know if it’s the same error (it probably is and i’m working on a fix for you)
English
@andrewfarah 3.13 is not < 3.14 ?:)
Found python3 at ...python@3.13/bin/python3 (3.13.7, arm64).
Unable to find a compatible Python runtime for Qwen.
Requirements: Apple Silicon (arm64), Python >= 3.10 and < 3.14, and access to mlx wheels.
Try: brew install python@3.12
English
@AKurian001 .rad file format is used by Reality Adlib Tracker - 3eality.com/productions/re…
English
Gaussian Splats in VR is about to get lot more exciting with RAD format, thanks to Spark 2.0. Below is an example of streaming .rad file in Vision Pro, real time rendering, on device, instantly.
Splats by:
WorldLabs and Andrii Shramko
More about .rad file below:
sparkjs.dev/2.0.0-preview/ github.com/sparkjsdev/spa… [MIT license]
English
more importantly you can play with what that original post evolved into over a year apptron.dev
English
if i had enough github sponsors asking for wasm sandboxing for AI we'd have it over a year ago but i have so much more on my plate and severely underfunded with little help. regardless, watch this space
Jeff Lindsay@progrium
after 9 months i fucking did it. vscode and full linux dev environment (with networking) in the browser. zero cloud needed. ~just serving static files~
English
@superhoge would be nice to have some examples to start with something instead of empty state
English
Vibecoding a Three.js TSL Node Editor. It lets you edit Three.js TSL using a node-based UI, and then export it as glTF. github.com/takahirox/tsl-… #threejs #tsl #gltf #vibecoding
English