Zarek Voss

[Zarek Voss @ZarekVoss]

opensource alternative to suno and udio 👌

[ACE Studio @ACEStudio_en]

We’re excited to release ACE-Step / ACE-Step-v1-3.5B, a fast, versatile DiT-based foundation model for music generation that runs on consumer-grade GPUs.

With its simple architecture and low hardware requirements, it’s easy to fine-tune for various music tasks, empowering, not replacing, artists and creators.

Think of it as a step toward music’s Stable Diffusion moment.

※ Trained on authorized, purchased data.
Demo Page: https://t.co/tVc8xCZfdO
Hugging Face: https://t.co/9sjZ5Dntvv
Git repo: https://t.co/AzHEwgmZgr

[Zarek Voss @ZarekVoss]

@_mohansolo Congratulations 🥳

[Zarek Voss @ZarekVoss]

@reach_vb A very good week for open-source, good to see so many smaller models that can run locally on low end hardware.

[Zarek Voss @ZarekVoss]

@realmrfakename Based on Llama 3B and Apache 2.0 ??? no license conflict?

[Zarek Voss @ZarekVoss]

Interesting tech, will be useful for AI companion apps

[LemonSlice @LemonSliceAI]

Introducing Lemon Slice Live:
the first real-time audio-video AI model

Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model.

Here’s how we built it + a live demo! 👇

[Anas @projectanas]

Google knows how to UX

"Delete" and "Branch from here" seem like the most intuitive options, yet only Google offers them.

These are literally life-changing. No more wasted threads, or unnecessary new threads - you can just delete responses (including your own) and change the conversation trajectory.

[Zarek Voss @ZarekVoss]

@OriolVinyalsML @lmarena_ai Congrats to the team. Any news regarding the 10 million context models, which was mentioned long ago👀

[Zarek Voss @ZarekVoss]

@bindureddy And Gemini pro's 2 million context window

[Vaibhav (VB) Srivastav @reach_vb]

Mistral is back! Apache 2.0 licensed, 24B, 32K context, Multilingual 🔥

https://t.co/XlhRsGHxka

[Zarek Voss @ZarekVoss]

@venturetwins that might need ASI 😅

[Zarek Voss @ZarekVoss]

@venturetwins @HeyGen_Official Impressive, the voice seems a bit off, some background music would have enhanced it.

[Zarek Voss @ZarekVoss]

Gemini 2.0 Flash Thinking Experimental 01-21 has a 65536 output length.....interesting

[Zarek Voss @ZarekVoss]

@venturetwins @litcapital 🤣

[VideoLAN @videolan]

VLC automatic subtitles generation and translation based on local and open source AI models running on your machine working offline, and supporting numerous languages!
Demo can be found on our #CES2025 booth in Eureka Park.

[Zarek Voss @ZarekVoss]

@NVIDIAGeForce #GeForceRTX50

[Zarek Voss @ZarekVoss]

@NVIDIAGeForce #GeForceGreats

[Zarek Voss @ZarekVoss]

@NVIDIAGeForce @remedygames I need a graphics card simple as that😎 #GeForceGreats

[Zarek Voss @ZarekVoss]

@NVIDIAGeForce #GeForceGreats

[Zarek Voss @ZarekVoss]

@kimmonismus I bet she's vegan😁, but seriously impressive, the tattoos in the arms changing was the only noticeable flaw.

[Zarek Voss @ZarekVoss]

😂

[Paul Kuruvilla @RohitPaulK]

We've never fired an intern this quick